© 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 - 16k
    5. 37-GEMMASCOPE-RES-16K
    6. 4380
    Prev
    Next
    INDEX
    Explanations

    specific statistical measures and results related to medical or biological assays

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    %);
    -0.91
    %";
    -0.90
    ?";
    -0.90
    ...";
    -0.88
    /";
    -0.87
    )$;
    -0.83
    !";
    -0.82
    .";
    -0.81
    /");
    -0.81
    :";
    -0.80
    POSITIVE LOGITS
     nakalista
    0.55
     agujeros
    0.45
     pingente
    0.43
     defaultstate
    0.42
     tornillos
    0.42
    forhold
    0.41
     pegatinas
    0.41
     pescoço
    0.40
     senare
    0.40
     rocas
    0.40
    Activations Density 0.342%

    No Known Activations