© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 35878
    Prev
    Next
    INDEX
    Explanations

    specific animal names and references to legal or programming concepts

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

    leopard, panther, lion, antelope, Leopold, Camelopardalis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    /*
    -0.48
    momix
    -0.45
    /**
    -0.43
    />";
    -0.43
     bedienen
    -0.40
    \"");
    -0.39
    ()")
    -0.39
     Bix
    -0.38
    cún
    -0.37
     صفحۀ
    -0.36
    POSITIVE LOGITS
     Leopard
    2.23
     leopard
    2.22
    Leopard
    2.20
    leopard
    1.93
     leop
    1.66
     leopardo
    1.40
    Leopold
    1.20
     Leopold
    1.19
    豹
    1.16
    opard
    0.88
    Activations Density 0.001%

    No Known Activations