© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 15642
    Prev
    Next
    INDEX
    Explanations

    words and phrases that indicate agreement or affirmation

    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
     bezpečnost
    -0.33
     OMITBAD
    -0.32
     sû
    -0.31
     étoient
    -0.31
     spørs
    -0.31
     solche
    -0.30
     ciertas
    -0.29
     gimana
    -0.28
     pří
    -0.28
     ہیں
    -0.28
    POSITIVE LOGITS
     had
    0.76
     have
    0.75
     drew
    0.63
     gave
    0.61
     comfortably
    0.60
     got
    0.60
     took
    0.59
     actively
    0.59
     confidently
    0.59
     reliably
    0.59
    Activations Density 0.269%

    No Known Activations