© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 6527
    Prev
    Next
    INDEX
    Explanations

    references to numerical data or statistics related to health

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

    HTML or equation markup

    np_acts-logits-general · gemini-2.0-flash

    menu item or union

    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
     tartalomajánló
    -1.24
    GEBURTSDATUM
    -1.13
     المعيارى
    -1.10
    :+:
    -1.03
    RectangleBorder
    -0.99
     الرياضيه
    -0.96
    aarrggbb
    -0.95
    DIPSETTING
    -0.94
     Roskov
    -0.93
     estekak
    -0.93
    POSITIVE LOGITS
    <h3>
    0.58
    <b>
    0.56
    <h2>
    0.54
    <i>
    0.52
    <h4>
    0.49
    et
    0.49
    <h6>
    0.49
    </td>
    0.48
    <h5>
    0.47
    &#
    0.46
    Activations Density 0.217%

    No Known Activations