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. 16322
    Prev
    Next
    INDEX
    Explanations

    code-related syntax components and structure

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

    Code, math, or numbers

    np_acts-logits-general · gemini-2.0-flash

    Sint, Delta, atomic, pool, total

    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
    verwijspagina
    -0.77
     contextLoads
    -0.74
     $_"
    -0.73
    OGND
    -0.71
    thâu
    -0.70
    tagHelperRunner
    -0.69
     ujednoznacz
    -0.66
     يتيمه
    -0.66
     Wikiseite
    -0.66
    (!__
    -0.64
    POSITIVE LOGITS
     odeur
    0.34
    ↵↵↵
    0.33
     embalaje
    0.32
     emballage
    0.31
     متعلقه
    0.31
     incendie
    0.31
     philosophie
    0.31
     infancia
    0.31
     directos
    0.30
     impresión
    0.30
    Activations Density 1.621%

    No Known Activations