© 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. 35-GEMMASCOPE-RES-16K
    11. 11028
    Prev
    Next
    INDEX
    Explanations

    scientific terms related to density and energy in various contexts

    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
     Disability
    -0.32
    ော
    -0.31
    DropDown
    -0.31
    Didier
    -0.31
    ガジン
    -0.31
     Fletcher
    -0.29
    っこう
    -0.29
    槛
    -0.29
    Tween
    -0.28
    Maverick
    -0.28
    POSITIVE LOGITS
     density
    3.31
     Density
    2.91
    density
    2.80
     densities
    2.73
    Density
    2.72
     DENSITY
    2.66
     densidad
    2.66
     densité
    2.56
    密度
    2.50
     dense
    2.47
    Activations Density 1.137%

    No Known Activations