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

    Neuronpedia

    Jacobian LensNEW
    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. 15056
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references to court cases

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

    nouns that refer to specific entities or objects in legal and news contexts.

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

    the word "The" at the beginning of sentences.

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

    determiners and possessive markers that introduce or specify noun phrases, especially the definite article.

    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
    ngrx
    -0.52
    ⟬
    -0.41
    
    -0.40
     cref
    -0.39
     Verhältnisse
    -0.38
    AppMethodBeat
    -0.37
     hereof
    -0.36
     verschieden
    -0.36
     hence
    -0.35
     {?}
    -0.35
    POSITIVE LOGITS
     announcement
    0.65
     lawsuit
    0.65
     accusation
    0.62
     incident
    0.61
     investigation
    0.60
     automaker
    0.58
     spokeswoman
    0.58
     complaint
    0.56
     prosecutor
    0.56
     revelation
    0.55
    Activations Density 0.607%

    No Known Activations