© 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. 9-GEMMASCOPE-RES-16K
    11. 11149
    Prev
    Next
    INDEX
    Explanations

    technical terms and codes related to protocols and performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    instances of "pt" in programming code, particularly when used as a parameter or property tree variable.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    */
    -0.40
     */
    -0.39
    }
    -0.36
    Ӕ
    -0.35
    .";
    -0.35
    );
    -0.35
    _;
    -0.34
    .");
    -0.34
    ]++;
    -0.33
    ."));
    -0.33
    POSITIVE LOGITS
     HT
    0.93
    FT
    0.91
     MT
    0.90
     GT
    0.88
     PT
    0.88
    MT
    0.87
    HT
    0.86
     DT
    0.86
     FT
    0.86
     ST
    0.84
    Activations Density 0.481%

    No Known Activations