© 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. 9234
    Prev
    Next
    INDEX
    Explanations

    names and indices associated with individuals or entities

    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
     samfun
    -0.34
     anywhere
    -0.34
    jména
    -0.31
     duros
    -0.30
     pañ
    -0.29
    着丈
    -0.29
     ARI
    -0.29
     `/
    -0.28
     ín
    -0.28
    føring
    -0.28
    POSITIVE LOGITS
    agle
    0.54
    AnchorStyles
    0.54
    essler
    0.53
    CppMethod
    0.53
    entz
    0.52
    add
    0.51
    unn
    0.50
    afford
    0.50
    udd
    0.50
    regler
    0.50
    Activations Density 0.520%

    No Known Activations