© 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. 15432
    Prev
    Next
    INDEX
    Explanations

    coordinating conjunctions and related transitional phrases

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

    emphasis or importance

    np_acts-logits-general · gemini-2.0-flash

    above, most, foremost

    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
     nahilalakip
    -0.80
    Diweddarwch
    -0.63
     Wiktionnaire
    -0.61
    fjspx
    -0.61
    newBuilder
    -0.59
     estekak
    -0.58
    ("-");
    -0.57
    erdings
    -0.57
    owels
    -0.56
     myſelf
    -0.56
    POSITIVE LOGITS
     above
    2.44
    Above
    2.26
    above
    2.20
     Above
    2.19
     ABOVE
    1.87
     most
    1.75
     acima
    1.74
    ABOVE
    1.47
     przede
    1.44
    most
    1.43
    Activations Density 0.206%

    No Known Activations