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-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3603
    Prev
    Next
    INDEX
    Explanations

    references to authors and citations in scientific literature

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

    journal articles

    np_acts-logits-general · gemini-2.0-flash

    scientific publication authors

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     Wachs
    -0.45
    numerusform
    -0.42
     Krause
    -0.42
     unknowingly
    -0.40
     Reim
    -0.40
    InSection
    -0.40
     somehow
    -0.39
     senhora
    -0.38
     Fleisch
    -0.37
    dungen
    -0.37
    POSITIVE LOGITS
     nahilalakip
    0.85
     Wikimedijinoj
    0.79
    WebVitals
    0.74
    yarnpkg
    0.73
    хьтан
    0.71
     gynhyrchwyd
    0.70
     kasarigan
    0.68
    цездатний
    0.68
     autorytatywna
    0.67
    новниш
    0.66
    Activations Density 0.909%

    No Known Activations