© 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. 9908
    Prev
    Next
    INDEX
    Explanations

    programming-related command patterns, specifically function calls and control structures

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

    opening parentheses in function calls and method invocations.

    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
    iſchen
    -0.70
    niſſe
    -0.64
     queſto
    -0.64
    ſicht
    -0.63
     виправивши
    -0.62
    verwijs
    -0.60
     imagui
    -0.60
    ſſung
    -0.59
     Photocase
    -0.59
    EDEFAULT
    -0.59
    POSITIVE LOGITS
     him
    0.56
     them
    0.38
    complexContent
    0.32
     ihm
    0.32
     companhia
    0.31
     vivienda
    0.30
     ouvrage
    0.27
     negociación
    0.27
     exploración
    0.27
    HasIndex
    0.26
    Activations Density 0.248%

    No Known Activations