© 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. 3594
    Prev
    Next
    INDEX
    Explanations

    code-related structures and syntax

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

    Tokens related to numbers or indexing

    np_acts-logits-general · gemini-2.0-flash

    predicting numeric phone values

    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
    MigrationBuilder
    -0.84
    alone
    -0.47
     <<<<<<<<<<<<<<
    -0.47
     архивлан
    -0.47
    κρι
    -0.45
    WriteBarrier
    -0.45
     Ante
    -0.45
     Ton
    -0.45
    testify
    -0.45
    Ton
    -0.45
    POSITIVE LOGITS
     num
    3.23
    num
    3.12
    Num
    2.76
     Num
    2.56
    NUM
    2.09
     getNum
    1.97
     NUM
    1.90
    setNum
    1.89
    getNum
    1.83
     number
    1.70
    Activations Density 0.073%

    No Known Activations