© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 37-GEMMASCOPE-RES-16K
    6. 6276
    Prev
    Next
    INDEX
    Explanations

    legal terms and references related to rights and responsibilities

    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
    </blockquote>
    -0.69
    ";
    -0.48
    RotationOrder
    -0.42
    
    -0.40
    </h3>
    -0.39
     resourceCulture
    -0.39
    =?";
    -0.39
    ';
    -0.38
    ";
    
    -0.38
    `;
    -0.37
    POSITIVE LOGITS
    .”)
    1.56
    。)
    1.41
    .)}
    1.34
    .")
    1.30
    »).
    1.28
    !)
    1.26
     »)
    1.25
    ?")
    1.21
    ”).
    1.19
    ")}
    1.17
    Activations Density 1.259%

    No Known Activations