© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 40-GEMMASCOPE-RES-16K
    11. 1069
    Prev
    Next
    INDEX
    Explanations

    structured mathematical expressions and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •Error Type Prediction

    No Comments

    Negative Logits
    ロウィン
    -1.28
    <unused52>
    -1.25
    <unused21>
    -1.23
    <unused16>
    -1.23
    <unused68>
    -1.23
    <unused79>
    -1.23
    [@BOS@]
    -1.23
    <unused14>
    -1.23
    <unused8>
    -1.23
    <unused3>
    -1.23
    POSITIVE LOGITS
    scriptcase
    0.19
    <unused63>
    0.12
     chrétien
    0.11
    <unused61>
    0.08
    LEGGI
    0.07
     ***!
    0.06
    <unused60>
    0.06
     vœ
    0.06
     húmedo
    0.06
    <unused62>
    0.04
    Activations Density 3.351%

    No Known Activations