© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 105711
    Prev
    Next
    INDEX
    Explanations

    numerical data, particularly statistics and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     geti
    -0.38
     Potosí
    -0.36
     %}
    -0.35
    lenz
    -0.34
    ❊
    -0.32
     Armenian
    -0.32
     Popo
    -0.32
    </tfoot>
    -0.32
     hippocampus
    -0.32
    annu
    -0.32
    POSITIVE LOGITS
    parsedMessage
    0.65
    IVEREF
    0.59
    Portály
    0.59
     للاسماء
    0.57
    richTextPanel
    0.56
     defaultstate
    0.56
    OrBuilder
    0.55
     nonUne
    0.55
    ésultats
    0.55
    LEncoder
    0.55
    Activations Density 0.353%

    No Known Activations