© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 12366
    Prev
    Next
    INDEX
    Explanations

    patterns or structures in sequences of numbers or data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ()]);
    -0.77
     defaultstate
    -0.73
    "]];
    -0.73
     {}));
    -0.73
    }');
    -0.72
     Domes
    -0.70
     Krom
    -0.70
    }];
    -0.69
    ()];
    -0.68
    ]');
    -0.68
    POSITIVE LOGITS
    ftagPool
    0.86
    LEncoder
    0.67
     risol
    0.65
     getItemCount
    0.63
    initis
    0.63
     sprend
    0.60
    ביוגרפיה
    0.60
     Bonif
    0.60
     Diallo
    0.59
    //
    0.59
    Activations Density 0.097%

    No Known Activations