© 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. 6493
    Prev
    Next
    INDEX
    Explanations

    programming language syntax elements, particularly related to function and method definitions

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

    function and method declarations with opening parentheses and curly braces.

    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
     linkovi
    -0.44
    sizeCache
    -0.44
    iodía
    -0.43
    MigrationBuilder
    -0.42
     hemsida
    -0.37
    onsored
    -0.37
    Personendaten
    -0.36
     igjen
    -0.36
    ckså
    -0.36
     ettei
    -0.36
    POSITIVE LOGITS
     super
    2.25
    super
    2.16
     SUPER
    1.60
     Super
    1.55
    Super
    1.50
    SUPER
    1.41
     супер
    1.38
     fuper
    1.30
     súper
    1.25
    超
    1.21
    Activations Density 0.202%

    No Known Activations