© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 35-GEMMASCOPE-RES-16K
    11. 5122
    Prev
    Next
    INDEX
    Explanations

    terms related to bulls and bulkiness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/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.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cos
    -0.41
    {#
    -0.37
     Potter
    -0.36
    Koordinaten
    -0.35
    ولوج
    -0.34
     foot
    -0.33
    Cos
    -0.31
    :][
    -0.30
    empre
    -0.30
     conducts
    -0.30
    POSITIVE LOGITS
     BULL
    1.09
    Bull
    1.09
     bull
    1.09
     Bull
    1.03
    BULL
    0.99
    bull
    0.96
     bul
    0.87
     Bul
    0.85
     Bulls
    0.84
     bulls
    0.84
    Activations Density 0.156%

    No Known Activations