© 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-2-9B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 2499
    Prev
    Next
    INDEX
    Explanations

    patterns of commas and whitespace in structured data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gesetze
    -0.35
     gewel
    -0.33
     berlebihan
    -0.32
    jenigen
    -0.32
     Latein
    -0.31
     hebat
    -0.31
     latein
    -0.31
     Einfluß
    -0.30
     gobier
    -0.30
     Handlungen
    -0.30
    POSITIVE LOGITS
    Tembelea
    0.97
     estekak
    0.76
    httphttps
    0.74
    帖最后由
    0.74
    SequentialGroup
    0.74
    exitRule
    0.73
    jsxFileName
    0.73
    zzleHttp
    0.72
     propOrder
    0.71
     kaarangay
    0.70
    Activations Density 0.297%

    No Known Activations