© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 775
    Prev
    Next
    INDEX
    Explanations

    phrases that explain causes or justifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Audiodateien
    -0.95
     StatefulWidget
    -0.84
    expandindo
    -0.82
    Démographie
    -0.79
     Khart
    -0.77
     समीक्षक
    -0.75
    extAlignment
    -0.74
    delaire
    -0.74
    hematical
    -0.72
    orgeous
    -0.72
    POSITIVE LOGITS
     why
    1.42
     reasons
    1.30
     reason
    1.27
    reasons
    1.19
     Reasons
    1.17
    why
    1.15
    Reasons
    1.10
     Reason
    1.10
    Reason
    1.08
     REASON
    1.06
    Activations Density 0.122%

    No Known Activations