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

    Neuronpedia

    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. 8100
    Prev
    Next
    INDEX
    Explanations

    HTML or markup tags

    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
    """
    -0.48
    ].
    -0.44
    );
    -0.42
    】
    -0.42
    ).
    -0.41
    ">
    -0.41
    ];
    -0.40
    .
    -0.40
    <h4>
    -0.39
    */
    -0.39
    POSITIVE LOGITS
     colspan
    1.18
     rowspan
    1.00
    
    0.94
     المعيارى
    0.90
    iſchen
    0.88
    ſicht
    0.88
    niſſe
    0.84
    ſchaft
    0.84
     MainAxisSize
    0.82
    ロウィン
    0.82
    Activations Density 0.091%

    No Known Activations