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 - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 3253
    Prev
    Next
    INDEX
    Explanations

    financial data and numerical representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ations
    -0.68
    ———-
    -0.60
     ویکی‌پدیای
    -0.59
    tedì
    -0.56
    ación
    -0.55
     newState
    -0.54
    UNCH
    -0.54
    〢
    -0.53
    ticello
    -0.53
     Dyck
    -0.52
    POSITIVE LOGITS
     समीक्षाओं
    0.72
     boroughs
    0.72
    0
    0.72
    6
    0.71
    zigen
    0.70
    5
    0.70
    mybatisplus
    0.68
    unhofer
    0.68
     mergeFrom
    0.66
    7
    0.63
    Activations Density 1.135%

    No Known Activations