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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2822
    Prev
    Next
    INDEX
    Explanations

    programming syntax and structure related to objects and functions

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

    whitespace and formatting characters in code and structured data.

    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
     Rettung
    -0.30
    UNUSED
    -0.24
    Bronnen
    -0.22
    Примечания
    -0.20
     efectiva
    -0.19
     –
    -0.19
     Gelegenheit
    -0.19
     Ruhe
    -0.18
     współpracy
    -0.18
    genommen
    -0.18
    POSITIVE LOGITS
     EconPapers
    0.88
    ViewImports
    0.87
    -------
    0.87
    SBATCH
    0.82
    niſſe
    0.82
    addCriterion
    0.81
     vooz
    0.81
     disambiguazione
    0.81
     dieſe
    0.80
     verſch
    0.80
    Activations Density 0.976%

    No Known Activations