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. 15851
    Prev
    Next
    INDEX
    Explanations

    elements related to assembly metadata in programming documentation

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

    Assembly and related terms in code

    np_acts-logits-general · gemini-2.0-flash

    .NET assembly attributes

    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
    enumii
    -0.60
     Exactos
    -0.56
    errHandler
    -0.56
    WriteBarrier
    -0.51
    ScopeManager
    -0.48
    :✨
    -0.47
    letar
    -0.47
     Administrativna
    -0.46
    NameInMap
    -0.46
     ویکی‌پدی
    -0.46
    POSITIVE LOGITS
    Assembly
    0.66
     AssemblyVersion
    0.64
     Assembly
    0.63
     Asamblea
    0.58
     AssemblyTitle
    0.54
     ASSEMBLY
    0.52
     assembly
    0.52
    assembly
    0.50
     ComVisible
    0.48
    InteropServices
    0.47
    Activations Density 0.069%

    No Known Activations