© 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. 20-GEMMASCOPE-RES-16K
    6. 7105
    Prev
    Next
    INDEX
    Explanations

    terms associated with functionality and usability in web applications

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

    simplification or ease

    np_acts-logits-general · gemini-2.0-flash

    simplifies or makes easier

    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
     JpaRepository
    -0.67
    SpringBootTest
    -0.61
    帖最后由
    -0.49
    Referanser
    -0.48
    NewRow
    -0.48
     scol
    -0.47
    JAXB
    -0.45
     hende
    -0.45
     inconclusive
    -0.45
     contradictory
    -0.45
    POSITIVE LOGITS
     simplifies
    2.00
     simplify
    1.96
     simplifying
    1.81
     ease
    1.73
     convenience
    1.73
     Simplify
    1.68
     simplification
    1.61
     simplified
    1.59
     easier
    1.58
     simplif
    1.55
    Activations Density 0.594%

    No Known Activations