© 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. 3126
    Prev
    Next
    INDEX
    Explanations

    statistical and mathematical terms associated with measurements and calculations

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

    Mathematical calculations and measurements

    np_acts-logits-general · gemini-2.0-flash

    calculation after "was" or "were"

    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
     BorderSide
    -0.47
    toon
    -0.44
     thiệu
    -0.44
    CodedInputStream
    -0.44
     estekak
    -0.44
     <",
    -0.43
     Continuum
    -0.42
    IsMutable
    -0.41
     penyer
    -0.41
    ijnt
    -0.41
    POSITIVE LOGITS
     calculation
    2.88
     calculate
    2.72
     calculating
    2.69
     calculations
    2.67
     calculated
    2.57
     Calculation
    2.54
     calculates
    2.49
     calcul
    2.47
    calculation
    2.39
     Calculations
    2.38
    Activations Density 1.049%

    No Known Activations