Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 9057
    Prev
    Next
    INDEX
    Explanations

    return statements in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GenerationType
    -0.99
     mapStateToProps
    -0.80
    ConstraintMaker
    -0.73
    .";
    
    -0.65
    aarrggbb
    -0.64
    ?";
    -0.60
    NUMX
    -0.60
    ";
    
    -0.60
    awtextra
    -0.59
    !?"
    -0.58
    POSITIVE LOGITS
     false
    0.73
     true
    0.66
     void
    0.59
     Unit
    0.57
     quiet
    0.56
     thôi
    0.55
    accio
    0.53
    upyter
    0.53
     Quiet
    0.53
     Early
    0.52
    Activations Density 0.069%

    No Known Activations