© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3766
    Prev
    Next
    INDEX
    Explanations

    references to animals, particularly tigers and wolves, as well as associated terms

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

    references to animals, especially tigers and wolves.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    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
     Cale
    -0.54
     Largo
    -0.48
     =
    
    -0.43
    cui
    -0.42
    journ
    -0.40
    gdx
    -0.40
    rief
    -0.40
    粹
    -0.39
     Gains
    -0.39
    tled
    -0.39
    POSITIVE LOGITS
     enfans
    0.94
     serpiente
    0.87
    onMouse
    0.73
    Mouse
    0.70
     conejo
    0.70
     kapture
    0.69
     vétérina
    0.69
     Teufel
    0.67
     Mouse
    0.67
     ennemi
    0.67
    Activations Density 0.325%

    No Known Activations