© 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. 12691
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific equations and physical processes

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

    Mathematical equations and formulas

    np_acts-logits-general · gemini-2.0-flash

    following equation

    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
    AddTagHelper
    -0.69
     ***!
    -0.66
    Portail
    -0.61
     saites
    -0.56
    awtextra
    -0.56
    Portale
    -0.55
     nahilalakip
    -0.55
    DoubleQuotes
    -0.52
    Tup
    -0.52
    MigrationBuilder
    -0.51
    POSITIVE LOGITS
     equation
    1.50
     formula
    1.44
     equations
    1.42
     formulas
    1.41
     formulae
    1.32
     Equation
    1.22
     expression
    1.22
    formula
    1.19
     expressions
    1.18
     formule
    1.18
    Activations Density 1.417%

    No Known Activations