© 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. 41-GEMMASCOPE-RES-16K
    11. 6285
    Prev
    Next
    INDEX
    Explanations

    references to deprecated technology or methods in coding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <h5>
    -1.02
    .)
    -0.82
    .»
    -0.75
    ."]
    -0.71
    .]
    -0.68
    </em>
    -0.68
    </h5>
    -0.67
    </u>
    -0.67
    。）
    -0.66
    .');
    -0.66
    POSITIVE LOGITS
    ".
    1.68
    '".
    1.42
    )".
    1.40
    ?".
    1.35
    ”.
    1.34
    '.
    1.33
     ".
    1.33
    }".
    1.30
    !".
    1.28
    """.
    1.26
    Activations Density 0.525%

    No Known Activations