Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 14436
    Prev
    Next
    INDEX
    Explanations

    HTML closing tags

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

    HTML tags (bold, italics, underline)

    np_acts-logits-general · gemini-2.0-flash

    bold text or 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
    ^(@)
    -1.01
    BibitemShut
    -0.95
    脚注の使い方
    -0.94
     getF
    -0.90
     rhestr
    -0.87
     ویکی‌پدیای
    -0.84
    /−
    -0.81
    windowFixed
    -0.81
     SwitchCompat
    -0.80
    PreferredItem
    -0.80
    POSITIVE LOGITS
    <strong>
    1.16
    <em>
    1.15
    <u>
    1.02
    </strong>
    0.93
    s
    0.92
    <b>
    0.89
    </em>
    0.83
    <i>
    0.82
    </sup>
    0.75
    ‘
    0.74
    Activations Density 0.202%

    No Known Activations