© 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. 5464
    Prev
    Next
    INDEX
    Explanations

    references to electronic media formats and editions

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

    Tokens that come before "CD", "DCs", "licit", "lic" or "FA"

    np_acts-logits-general · gemini-2.0-flash

    words starting with E

    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
     FANDOM
    -0.65
    ConstraintMaker
    -0.63
    WriteTagHelper
    -0.58
    IntoConstraints
    -0.57
    cracked
    -0.56
    égard
    -0.56
    جراء
    -0.55
    amitié
    -0.54
     архивлан
    -0.54
    RIER
    -0.53
    POSITIVE LOGITS
     mails
    0.53
     Ename
    0.49
     ven
    0.47
     ename
    0.47
     wijk
    0.46
    os
    0.45
     strå
    0.44
     asy
    0.44
     gjø
    0.43
     eruption
    0.43
    Activations Density 0.292%

    No Known Activations