© 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. 30-GEMMASCOPE-RES-16K
    11. 12496
    Prev
    Next
    INDEX
    Explanations

    numerical statistics and data metrics

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

    Code, stats, and numeric quantities

    np_acts-logits-general · gemini-2.0-flash

    numerical summaries and counts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/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.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     պ
    -0.30
     arbitrarily
    -0.29
     заранее
    -0.28
     Estamos
    -0.26
    anywhere
    -0.26
     AROUND
    -0.26
    适当
    -0.25
     Gegenstand
    -0.25
     другого
    -0.25
     Ansch
    -0.25
    POSITIVE LOGITS
     total
    0.99
     totale
    0.85
     Total
    0.84
     average
    0.83
     percentage
    0.77
    total
    0.75
    Total
    0.74
     ratio
    0.73
     TOTAL
    0.73
     avg
    0.71
    Activations Density 1.138%

    No Known Activations