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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 104744
    Prev
    Next
    INDEX
    Explanations

    semicolons in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ſelben
    -1.23
    mpagne
    -1.21
    ſſung
    -1.19
     geſch
    -1.18
     ſei
    -1.18
    <unused14>
    -1.17
    <unused23>
    -1.17
    <unused8>
    -1.17
    <pad>
    -1.17
    [@BOS@]
    -1.17
    POSITIVE LOGITS
    ;
    0.76
    .
    0.75
    </tr>
    0.64
    ?
    0.52
    ;
    
    0.50
    !
    0.50
     ;
    0.50
    ,
    0.50
    );
    0.48
    };
    0.48
    Activations Density 0.003%

    No Known Activations