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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 3844
    Prev
    Next
    INDEX
    Explanations

    data types and mathematical entities related to programming and numerical analysis

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

    Mathematical symbols and nonnegative integers

    np_acts-logits-general · gemini-2.0-flash

    unsigned integers and counts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.55
    tagHelperRunner
    -0.51
    Aholisi
    -0.46
     
    -0.46
    addCriterion
    -0.44
     الرياضيه
    -0.43
    RenderAtEndOf
    -0.42
    ỡng
    -0.42
    хьтан
    -0.42
     nahilalakip
    -0.42
    POSITIVE LOGITS
    unsigned
    0.93
     unsigned
    0.86
    uint
    0.86
     uint
    0.76
    NSUInteger
    0.69
    UInt
    0.65
     usize
    0.63
     UInt
    0.62
    Unsigned
    0.62
    Uint
    0.60
    Activations Density 0.634%

    No Known Activations