© 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. 9009
    Prev
    Next
    INDEX
    Explanations

    references to the number "one" in various contexts

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

    Follows the word "one"

    np_acts-logits-general · gemini-2.0-flash

    the word one

    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
     defStyleAttr
    -0.68
     ―――――
    -0.62
     ſch
    -0.60
    dır
    -0.58
    ndash
    -0.56
    tably
    -0.56
    Portale
    -0.56
    denly
    -0.56
    fully
    -0.55
    Pautan
    -0.55
    POSITIVE LOGITS
     hundred
    1.04
    iric
    0.95
     thing
    0.92
     sided
    0.81
    hundred
    0.79
     Hundred
    0.78
     thousand
    0.76
    ReusableCell
    0.75
     million
    0.73
     liners
    0.71
    Activations Density 0.156%

    No Known Activations