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

    Neuronpedia

    APICircuit 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. 20-GEMMASCOPE-RES-16K
    6. 2978
    Prev
    Next
    INDEX
    Explanations

    markup or HTML elements in the text

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

    HTML or code-related formatting

    np_acts-logits-general · gemini-2.0-flash

    end of sentences or code sections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    れ
    -0.56
    +#+#
    -0.54
    ⓧ
    -0.50
     Constitucional
    -0.50
    دانشنامهٔ
    -0.49
    stdafx
    -0.49
    Personendaten
    -0.49
    quelize
    -0.49
     Italijani
    -0.48
     Anzeigen
    -0.48
    POSITIVE LOGITS
    </table>
    1.18
    </tbody>
    0.76
    \{\\
    0.71
    <tfoot>
    0.63
    </thead>
    0.63
     الحره
    0.57
    campista
    0.57
    mtable
    0.57
    IsContent
    0.56
    <tbody>
    0.56
    Activations Density 0.029%

    No Known Activations