© 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. 3518
    Prev
    Next
    INDEX
    Explanations

    patterns of numeric sequences and specific numerical values

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

    Times in half-hour increments

    np_acts-logits-general · gemini-2.0-flash

    X:A.M./P.M. times

    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
    WriteBarrier
    -0.86
    цездатний
    -0.84
    ViewFeatures
    -0.72
    IsMutable
    -0.69
     فريبيس
    -0.68
    исленность
    -0.65
     Мексичка
    -0.65
    WebMethod
    -0.64
    istica
    -0.63
    SourceChecksum
    -0.63
    POSITIVE LOGITS
     pm
    0.52
     PM
    0.50
    PM
    0.50
    pm
    0.49
    noon
    0.48
     cuenta
    0.47
    CPM
    0.45
     tæ
    0.41
    онов
    0.40
     midday
    0.40
    Activations Density 0.046%

    No Known Activations