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. 13843
    Prev
    Next
    INDEX
    Explanations

    references to academic journals and publication details

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

    Numbers enclosed in parentheses or brackets

    np_acts-logits-general · gemini-2.0-flash

    volume, issue, year

    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
     للمعارف
    -0.63
    Personendaten
    -0.60
    +#+#
    -0.60
    webElementGuid
    -0.56
    ectady
    -0.55
     nahilalakip
    -0.54
     BoxFit
    -0.54
    RenderAtEndOf
    -0.54
    ValueStyle
    -0.53
    AccessorTable
    -0.52
    POSITIVE LOGITS
    TestingModule
    0.55
     Volume
    0.46
     volume
    0.44
    Ausgabe
    0.42
    Volume
    0.41
     Ausgabe
    0.41
     Volumen
    0.39
    ésultat
    0.39
     year
    0.38
    guenos
    0.38
    Activations Density 0.690%

    No Known Activations