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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 108421
    Prev
    Next
    INDEX
    Explanations

    terms related to safety, compliance, and ethical considerations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    insurance premiums, braking performance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kaarangay
    -0.37
    Bromoform
    -0.36
     autorytatywna
    -0.36
     Ause
    -0.35
     frattempo
    -0.35
    Diweddarwch
    -0.34
     Dread
    -0.33
     Paglinawan
    -0.33
     forth
    -0.33
    atchewan
    -0.33
    POSITIVE LOGITS
    MessageTagHelper
    0.53
    Selfer
    0.48
    出版年
    0.46
     חיצוניים
    0.46
    EndGlobalSection
    0.45
    AsyncResult
    0.44
    Життєпис
    0.43
     abar
    0.43
     ligiloj
    0.43
    detectChanges
    0.42
    Activations Density 0.188%

    No Known Activations