© 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. 20-GEMMASCOPE-RES-16K
    11. 8377
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and inequalities related to functions, limits, and algebraic properties

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

    Mathematical variable before an exponent

    np_acts-logits-general · gemini-2.0-flash

    powers and exponents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    KommentareTeilen
    -0.62
    farwyddwr
    -0.58
     Associated
    -0.48
    EndInit
    -0.47
    apimachinery
    -0.47
     localObject
    -0.47
    BindingResult
    -0.47
    Associated
    -0.45
    cesz
    -0.44
    칼
    -0.44
    POSITIVE LOGITS
     power
    1.37
    power
    1.24
    POWER
    1.19
    Power
    1.17
     exponent
    1.17
     powers
    1.17
     POWER
    1.16
     Power
    1.16
    pow
    1.10
     exponents
    1.10
    Activations Density 1.631%

    No Known Activations