Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 6113
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with "wh" sounds, indicating a focus on interrogative expressions or inquiries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Abia
    -0.62
    edonia
    -0.50
    utah
    -0.49
    ransition
    -0.48
    weaver
    -0.48
    profen
    -0.47
     Arlene
    -0.47
     Crusoe
    -0.47
    ekt
    -0.47
     Helena
    -0.47
    POSITIVE LOGITS
    Wh
    1.48
     Wh
    1.48
     wh
    1.44
    wh
    1.38
     WH
    1.38
    WH
    1.23
     WHIT
    1.02
     Whit
    0.99
     Whi
    0.95
    Whit
    0.94
    Activations Density 0.201%

    No Known Activations