© 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. 31-GEMMASCOPE-RES-16K
    11. 4896
    Prev
    Next
    INDEX
    Explanations

    programming language syntax elements, particularly related to class declarations and definitions

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

    class inheritance declarations (the colon symbol following a class name that introduces parent classes).

    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
    Vorlage
    -0.35
    UrlResolution
    -0.34
    reactstrap
    -0.34
    batore
    -0.34
     recensement
    -0.33
     isoto
    -0.32
     Dodson
    -0.31
    醐
    -0.31
    inova
    -0.31
    intios
    -0.31
    POSITIVE LOGITS
     public
    2.58
    public
    2.23
     PUBLIC
    1.89
     Public
    1.87
    Public
    1.84
     pública
    1.84
     público
    1.84
     públicas
    1.75
     públicos
    1.75
     publicly
    1.73
    Activations Density 0.291%

    No Known Activations