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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 12-GEMMASCOPE-RES-16K
    6. 12733
    Prev
    Next
    INDEX
    Explanations

    code-related operations that involve setting or modifying parameters, particularly in the context of handling credentials and HTTP requests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    👈
    -0.50
     memu
    -0.42
     admitted
    -0.41
    FunctionFlags
    -0.41
     admit
    -0.40
     arran
    -0.39
     angesch
    -0.39
     apro
    -0.37
     lưu
    -0.36
    RequestMethod
    -0.36
    POSITIVE LOGITS
     الرياضيه
    0.90
    StoryboardSegue
    0.90
    IsMutable
    0.87
    qrstuvwxyz
    0.85
    المناصب
    0.78
     otomatig
    0.78
    GEBURTSDATUM
    0.75
    CopyWith
    0.75
    expandindo
    0.75
    ArrowToggle
    0.73
    Activations Density 0.461%

    No Known Activations