© 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
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 927
    Prev
    Next
    INDEX
    Explanations

    tokens related to textual formatting and punctuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    XmlAccessType
    -0.57
    UserScript
    -0.46
     שוליים
    -0.45
    Fel
    -0.45
    Fak
    -0.44
    fea
    -0.43
    MigrationBuilder
    -0.43
    fles
    -0.43
    fel
    -0.42
    centralwidget
    -0.42
    POSITIVE LOGITS
     fore
    1.82
     Fore
    1.77
    Fore
    1.72
    fore
    1.66
     FORE
    1.57
     Ford
    1.51
     Forrest
    1.50
    Ford
    1.47
    フォ
    1.46
    FORE
    1.46
    Activations Density 1.272%

    No Known Activations