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. 18-GEMMASCOPE-RES-16K
    6. 3623
    Prev
    Next
    INDEX
    Explanations

    strong emotional or impactful moments in narratives

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

    HTML formatting tags

    np_acts-logits-general · gemini-2.0-flash

    html formatting tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     كومونز
    -1.08
     ModelExpression
    -1.05
    MigrationBuilder
    -1.01
    олові
    -1.00
     Савезне
    -0.97
     beginnetje
    -0.95
    tonode
    -0.89
     disambiguazione
    -0.87
    WindowConstants
    -0.86
     الحره
    -0.86
    POSITIVE LOGITS
    <strong>
    1.94
    <em>
    1.80
    <b>
    1.70
    <i>
    1.49
    <u>
    1.41
    <code>
    1.09
    <sup>
    0.97
     
    0.93
    <sub>
    0.84
    <s>
    0.79
    Activations Density 0.023%

    No Known Activations