© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 9778
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and notations related to statistical concepts

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

    mathematical notation and LaTeX expressions containing variables and operators.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.82
     الرياضيه
    -0.73
    ViewImports
    -0.71
     صوتيه
    -0.70
     للاسماء
    -0.70
    WebVitals
    -0.68
     للمعارف
    -0.68
    الحياه
    -0.64
     برانيه
    -0.63
    RTLR
    -0.62
    POSITIVE LOGITS
     virgen
    0.38
     Polres
    0.32
     vecin
    0.30
     krep
    0.30
    处的
    0.29
    punto
    0.29
     patrulla
    0.29
     connaissance
    0.29
     rumbo
    0.28
     teneur
    0.28
    Activations Density 2.115%

    No Known Activations