© 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-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 2714
    Prev
    Next
    INDEX
    Explanations

    syntactic structures related to code block endings in programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    $\\
    -0.42
    Norman
    -0.40
     mien
    -0.40
    ryn
    -0.39
     Norman
    -0.39
     piece
    -0.39
    igh
    -0.39
    piece
    -0.38
     Rav
    -0.38
    爪
    -0.37
    POSITIVE LOGITS
    Hauptartikel
    1.03
    참고
    0.78
    Personendaten
    0.74
    IBOutlet
    0.72
    principalColumn
    0.70
    värr
    0.67
    tagHelperRunner
    0.67
    ConstraintMaker
    0.67
    IndentedString
    0.66
    UrlResolution
    0.66
    Activations Density 0.133%

    No Known Activations