© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 11903
    Prev
    Next
    INDEX
    Explanations

    phrases that reference personal relationships and interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the phrase "X was/is all about" used to describe or summarize what something represents or exemplifies.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou

    phrases expressing what something "is" or "was" in an emphatic or defining way, particularly in constructions like "what X is all about" or "what X was made for."

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    pronoun-led main clauses built around auxiliary or copular verbs (often with modals), especially in evaluative or explanatory statements.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     informée
    -0.59
    transQ
    -0.59
    
    -0.52
    Ƚ
    -0.52
    httphttps
    -0.50
    BeginContext
    -0.50
    -------
    -0.48
    σιμοποι
    -0.48
     snippetHide
    -0.48
     ISNI
    -0.47
    POSITIVE LOGITS
    WireFormatLite
    0.51
     strives
    0.43
     talked
    0.42
    SharedDtor
    0.42
    intios
    0.42
     brag
    0.42
     talk
    0.42
     strive
    0.42
    正
    0.40
     aspire
    0.40
    Activations Density 0.244%

    No Known Activations