© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1475
    Prev
    Next
    INDEX
    Explanations

    mathematical terms and symbols associated with physical theories

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

    "mu" follows "2" or math symbols

    np_acts-logits-general · gemini-2.0-flash

    2 followed by mu

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
     surla
    -1.12
     ſind
    -1.05
    WebElementEntity
    -1.03
     témoig
    -1.01
     ſei
    -1.01
    ſchaft
    -1.00
     Geſch
    -0.99
     geſch
    -0.98
    TagMode
    -0.96
     transfieras
    -0.95
    POSITIVE LOGITS
    ,
    0.44
    :
    0.41
    .
    0.40
    ;
    0.40
    ing
    0.40
     is
    0.36
     too
    0.36
    )
    0.35
     
    0.35
    1
    0.34
    Activations Density 0.145%

    No Known Activations