Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 2988
    Prev
    Next
    INDEX
    Explanations

    structured formatting elements in LaTeX documents

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

    LaTeX and XML/HTML markup tags and code structures.

    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
    NewLabel
    -0.45
    ‪
    -0.42
    createCanvas
    -0.35
    ấy
    -0.34
    catchError
    -0.34
    ngths
    -0.34
    Aire
    -0.33
    kuit
    -0.32
     ‪
    -0.32
    ospel
    -0.31
    POSITIVE LOGITS
    WithIOException
    0.71
    Tikang
    0.67
    awtextra
    0.57
     يتيمه
    0.55
    AccessorTable
    0.54
    selaer
    0.53
     okuyayım
    0.52
     estekak
    0.50
     initComponents
    0.50
    сылкі
    0.49
    Activations Density 0.032%

    No Known Activations