© 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. 20-GEMMASCOPE-RES-16K
    11. 7981
    Prev
    Next
    INDEX
    Explanations

    assertions and disclaimers related to allegations or accusations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    #+#
    -0.41
     gynhyrchwyd
    -0.38
    getWorld
    -0.35
     surla
    -0.34
     חיים
    -0.34
    ackerel
    -0.33
     chắn
    -0.33
    proses
    -0.32
    centralwidget
    -0.32
     capilla
    -0.31
    POSITIVE LOGITS
     misunder
    0.54
    ReusableCell
    0.52
    AutoScale
    0.48
     criticism
    0.46
     SqlDbType
    0.46
    propTypes
    0.45
    leva
    0.45
    </tfoot>
    0.44
     panicked
    0.44
     misunderstand
    0.44
    Activations Density 0.474%

    No Known Activations