© 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. 8291
    Prev
    Next
    INDEX
    Explanations

    the word "all" in various contexts

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

    "all"

    np_acts-logits-general · gemini-2.0-flash

    all types or quantities

    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
     allemaal
    -0.79
     모두
    -0.78
    BeginContext
    -0.76
    IndentedString
    -0.72
     épaules
    -0.70
     ognuno
    -0.68
     ciascuno
    -0.68
     ciasc
    -0.67
     genoux
    -0.66
    IUrlHelper
    -0.66
    POSITIVE LOGITS
     kinds
    1.21
     sorts
    1.20
     aspects
    0.93
     manner
    0.90
     types
    0.89
     three
    0.88
    uding
    0.86
     four
    0.86
    IANCE
    0.81
    lllll
    0.81
    Activations Density 0.167%

    No Known Activations