© 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-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 13521
    Prev
    Next
    INDEX
    Explanations

    the word "how" and its variations, indicating inquiries about processes or methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     raft
    -0.86
     Schulte
    -0.85
     Gegenteil
    -0.82
     Milne
    -0.80
     Münch
    -0.76
     tdi
    -0.76
     occaf
    -0.75
     Cæsar
    -0.75
    گي
    -0.75
     Balik
    -0.75
    POSITIVE LOGITS
     how
    1.88
     How
    1.57
     HOW
    1.57
    How
    1.46
    HOW
    1.37
    how
    1.25
     Howell
    1.07
    howto
    1.00
     Howe
    0.99
     what
    0.99
    Activations Density 0.074%

    No Known Activations