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. 31-GEMMASCOPE-RES-16K
    6. 16359
    Prev
    Next
    INDEX
    Explanations

    sequences of numbers or numerical values within a technical context

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

    Mathematical or programming notation

    np_acts-logits-general · gemini-2.0-flash

    programming and mathematical expressions

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    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
     Wikiseite
    -0.51
    contentLoaded
    -0.50
    quelize
    -0.44
    Kilder
    -0.43
    onedDateTime
    -0.41
    TypedDataSet
    -0.40
     klubben
    -0.40
     bolsillo
    -0.39
     hjemmeside
    -0.39
    aryen
    -0.39
    POSITIVE LOGITS
    tagHelperRunner
    0.74
     initComponents
    0.51
    ratic
    0.47
     FACTOR
    0.46
     Factor
    0.45
     intptr
    0.45
     jLabel
    0.43
     Стар
    0.43
     Roy
    0.43
    ăl
    0.43
    Activations Density 0.221%

    No Known Activations