© 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. 30-GEMMASCOPE-RES-16K
    11. 11534
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts and notations related to structures and functions

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

    Appears before "ex", "id", "in", "re", "Ob", or "Vol"

    np_acts-logits-general · gemini-2.0-flash

    vol, in, ex, id prefixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/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.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     snippetHide
    -0.81
     ModelExpression
    -0.81
     BoxFit
    -0.77
     autorytatywna
    -0.72
    principalColumn
    -0.72
    ſelves
    -0.71
    DrawerToggle
    -0.70
    resizingMask
    -0.68
    ロウィン
    -0.68
     Comprometido
    -0.68
    POSITIVE LOGITS
    s
    0.55
    C
    0.43
    A
    0.42
    O
    0.41
    I
    0.40
    H
    0.40
    R
    0.38
    S
    0.38
    D
    0.38
    N
    0.38
    Activations Density 0.242%

    No Known Activations