© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 8217
    Prev
    Next
    INDEX
    Explanations

    context indicating attendance at a college football game

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

    Follows a determiner or preposition

    np_acts-logits-general · gemini-2.0-flash

    a threat, a massive, some reasons

    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
     poichè
    -0.94
     feroit
    -0.84
     således
    -0.83
     ardından
    -0.83
     ainfi
    -0.81
     auroit
    -0.79
     ifølge
    -0.77
     ngunit
    -0.76
     nemlig
    -0.76
     endast
    -0.76
    POSITIVE LOGITS
     thing
    1.00
     stuff
    1.00
     [
    0.97
     really
    0.97
     uh
    0.95
     sort
    0.93
     kind
    0.93
     somebody
    0.91
     everybody
    0.88
     things
    0.84
    Activations Density 0.262%

    No Known Activations