© 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. 36-GEMMASCOPE-RES-16K
    11. 12182
    Prev
    Next
    INDEX
    Explanations

    JavaScript and programming language structures such as objects, functions, and syntax components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ")
    -0.45
    kloped
    -0.44
     "")
    -0.42
    kuuta
    -0.39
    ֔
    -0.38
    unknownFields
    -0.38
    ")
    -0.37
    だが
    -0.37
    Lähteet
    -0.36
    vantages
    -0.35
    POSITIVE LOGITS
    );
    2.03
    ");
    1.97
    "];
    1.93
    '];
    1.92
    ');
    1.90
    ];
    1.89
    ）；
    1.82
    )$;
    1.76
    .);
    1.76
     />;
    1.74
    Activations Density 1.242%

    No Known Activations