© 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. 22-GEMMASCOPE-RES-16K
    11. 2983
    Prev
    Next
    INDEX
    Explanations

    descriptions of items and clothing, particularly in relation to safety gear

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

    "hat" or words associated with "hats"

    np_acts-logits-general · gemini-2.0-flash

    hats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ContentAsync
    -0.63
    TagMode
    -0.62
     Muscles
    -0.55
    loroethene
    -0.55
     Muscle
    -0.55
    jø
    -0.54
     Contracts
    -0.53
    rungsseite
    -0.52
     ProtoMessage
    -0.52
    Kariera
    -0.51
    POSITIVE LOGITS
     hat
    1.55
     hats
    1.53
     Hat
    1.45
    Hat
    1.38
     Hats
    1.35
     HAT
    1.29
    Hats
    1.23
    hats
    1.16
     brim
    1.12
    hat
    1.12
    Activations Density 0.094%

    No Known Activations