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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 8-GEMMASCOPE-RES-16K
    11. 4240
    Prev
    Next
    INDEX
    Explanations

    terms related to actions, conditions, and relationships in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/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.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵↵
    -0.59
    Numerology
    -0.58
     >=",
    -0.54
    <eos>
    -0.47
     Tapatalk
    -0.46
    1
    -0.45
    Jeografia
    -0.45
    log
    -0.44
    <bos>
    -0.44
    </blockquote>
    -0.43
    POSITIVE LOGITS
     MainAxisSize
    1.07
     BoxDecoration
    1.04
    createServer
    0.99
    RectangleBorder
    0.98
    extAlignment
    0.97
    \{\\
    0.95
    ^(@)
    0.90
     Majefty
    0.84
    auteuil
    0.83
    ientras
    0.83
    Activations Density 2.172%

    No Known Activations