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. 19-GEMMASCOPE-RES-16K
    6. 3044
    Prev
    Next
    INDEX
    Explanations

    query strings and parameters typically associated with URLs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.67
    writeFieldEnd
    -0.57
     FormsModule
    -0.47
    pyplot
    -0.44
    CUSS
    -0.44
    abancı
    -0.43
    WEBPACK
    -0.42
    フォーマンス
    -0.41
    JComboBox
    -0.41
    ✨:
    -0.41
    POSITIVE LOGITS
    utm
    0.77
    httphttps
    0.73
     autorytatywna
    0.66
    KURZBESCHREIBUNG
    0.65
    fbc
    0.65
    amp
    0.63
    TagMode
    0.61
     /\.(
    0.60
     /\.
    0.59
    oflavin
    0.59
    Activations Density 0.083%

    No Known Activations