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. 10-GEMMASCOPE-RES-16K
    6. 3046
    Prev
    Next
    INDEX
    Explanations

    structured data related to films, including their duration and technical specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    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
    -0.52
    modb
    -0.48
    LookAnd
    -0.46
    DataAnnotations
    -0.43
     considérons
    -0.41
     JUGA
    -0.40
    nloa
    -0.40
    ald
    -0.39
    uken
    -0.39
    haus
    -0.39
    POSITIVE LOGITS
    ClientSize
    0.76
    CloseOperation
    0.72
     totalt
    0.70
    amaño
    0.69
     ویکی‌پدیای
    0.68
     total
    0.65
     purpoſe
    0.65
     getItemCount
    0.63
    MemoryWarning
    0.63
     становника
    0.62
    Activations Density 0.316%

    No Known Activations