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. 3136
    Prev
    Next
    INDEX
    Explanations

    elements and attributes in HTML or XML-like documents

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

    HTML or XML code snippets

    np_acts-logits-general · gemini-2.0-flash

    closing list item 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
    таратура
    -0.56
     ApiException
    -0.50
    RequiresApi
    -0.48
    enterOuterAlt
    -0.48
    hog
    -0.47
    +:+
    -0.47
    Hướng
    -0.46
    evich
    -0.46
    onViewCreated
    -0.45
    AxisAlignment
    -0.45
    POSITIVE LOGITS
    Kapcsolódó
    0.78
    glEnd
    0.72
    EndGlobalSection
    0.69
     '</
    0.67
     "</
    0.66
    </table>
    0.65
    </
    0.64
    "</
    0.62
    closures
    0.62
    )</
    0.60
    Activations Density 0.138%

    No Known Activations