© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 21094
    Prev
    Next
    INDEX
    Explanations

    repetitive patterns in code or structured data

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

    technical topics and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    AnchorTagHelper
    -0.42
    WithFormat
    -0.41
    ParallelGroup
    -0.40
     Vog
    -0.38
    ManyToMany
    -0.37
    multicolumn
    -0.36
    +:+
    -0.35
     Sinf
    -0.35
     VIDEOTAPE
    -0.35
     نفس
    -0.34
    POSITIVE LOGITS
     ſind
    0.62
    Personendaten
    0.62
    saraba
    0.59
     autorytatywna
    0.58
    aarrggbb
    0.57
    CppCodeGen
    0.56
    الدراسه
    0.52
     Cæsar
    0.52
     myſelf
    0.52
    WebElementEntity
    0.51
    Activations Density 0.039%

    No Known Activations