© 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. 22-GEMMASCOPE-RES-16K
    11. 14819
    Prev
    Next
    INDEX
    Explanations

    questions and statements concerning recommendations or advice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Fluss
    -0.37
     dix
    -0.36
    getValues
    -0.34
     localización
    -0.34
    fadeOut
    -0.33
    <eos>
    -0.33
     Raven
    -0.33
     Kome
    -0.32
     Ackerman
    -0.32
     bass
    -0.31
    POSITIVE LOGITS
    should
    1.00
    hould
    0.98
    Should
    0.96
     Should
    0.95
     should
    0.93
     SHOULD
    0.89
     ſhould
    0.85
    rungsseite
    0.80
     faudrait
    0.75
     ſind
    0.74
    Activations Density 0.112%

    No Known Activations