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-2-2B
    4. Residual Stream - 32k
    5. 12-GEMMASCOPE-RES-32K
    6. 1728
    Prev
    Next
    INDEX
    Explanations

    references to collective decision-making processes and authority within a community or organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_32k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    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
     Madura
    -0.49
    ाप्त
    -0.49
     doon
    -0.48
     myſelf
    -0.47
     biar
    -0.47
     Marne
    -0.46
     IndexError
    -0.46
     Jind
    -0.46
    fully
    -0.45
     exceeded
    -0.45
    POSITIVE LOGITS
    PhysRev
    0.90
     "..\..\..\
    0.82
     "..\..\
    0.78
    Portale
    0.78
    AddTagHelper
    0.77
    LookAnd
    0.77
     AssemblyCulture
    0.76
     estekak
    0.75
     للاسماء
    0.75
    fjspx
    0.74
    Activations Density 0.015%

    No Known Activations