© 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. 34
    Prev
    Next
    INDEX
    Explanations

    passive voice constructions

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

    the verb "is" used as a copula to describe or define nouns.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    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
     okuyayım
    -0.52
     виправивши
    -0.43
    verwijspagina
    -0.42
     jspb
    -0.41
     onOptions
    -0.39
    ChildIndex
    -0.35
     Red
    -0.35
    CopyWith
    -0.34
    надца
    -0.33
     Rem
    -0.32
    POSITIVE LOGITS
     comprised
    0.85
     composed
    0.73
     based
    0.71
     especially
    0.69
     særlig
    0.65
     overseen
    0.65
     accompanied
    0.64
     particularly
    0.63
     divided
    0.63
     للاسماء
    0.62
    Activations Density 0.731%

    No Known Activations