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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 1580
    Prev
    Next
    INDEX
    Explanations

    keywords and structures related to file validation processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    findpost
    -0.61
    parsedMessage
    -0.58
    OGND
    -0.57
    逅
    -0.57
    SEGUIR
    -0.54
    <?,
    -0.52
    leness
    -0.52
    Alike
    -0.52
    Referències
    -0.51
    sizeCache
    -0.50
    POSITIVE LOGITS
     list
    1.29
     List
    1.05
    list
    1.02
     listes
    0.97
     liste
    0.95
     lijst
    0.95
     lista
    0.94
    List
    0.93
     lists
    0.90
     listado
    0.89
    Activations Density 0.747%

    No Known Activations