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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 56993
    Prev
    Next
    INDEX
    Explanations

    references to geographic locations or identifiers related to the United States

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personensuche
    -1.12
    RenderAtEndOf
    -0.97
    IUrlHelper
    -0.89
    ScopeManager
    -0.82
    findpost
    -0.81
     ***!
    -0.79
    ագրություններ
    -0.77
     '\\;'
    -0.76
     تضيفلها
    -0.76
     Seeder
    -0.76
    POSITIVE LOGITS
     водя
    0.45
    ึกษา
    0.42
     dönt
    0.42
     része
    0.41
    usen
    0.41
     Soccerway
    0.41
     and
    0.41
     ci
    0.40
    Français
    0.39
     revanche
    0.39
    Activations Density 0.006%

    No Known Activations