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. 11-GEMMASCOPE-RES-16K
    6. 1583
    Prev
    Next
    INDEX
    Explanations

    positive evaluations or assessments of concepts, experiences, or products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -0.95
     zijne
    -0.76
     myſelf
    -0.76
     himſelf
    -0.75
     enfans
    -0.75
     ainfi
    -0.75
     vastaan
    -0.74
     skolan
    -0.74
     themſelves
    -0.74
     varandra
    -0.74
    POSITIVE LOGITS
    RegressionTest
    0.63
     autorytatywna
    0.63
    VIAF
    0.59
     SwiftUI
    0.59
    ᅠ
    0.58
     VIAF
    0.58
     Gre
    0.57
    省市镇
    0.57
     transférez
    0.56
    AddHtmlAttribute
    0.56
    Activations Density 0.531%

    No Known Activations