© 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
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 8667
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and formatting related to equations or mathematical expressions

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

    numerical coordinates in mathematical or graphical contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
    httphttps
    -0.45
    IVEREF
    -0.38
    новниш
    -0.37
    دانشنامهٔ
    -0.36
     meille
    -0.36
    Aholisi
    -0.35
    новништво
    -0.34
    ⎨
    -0.34
    Rhestr
    -0.33
    dération
    -0.33
    POSITIVE LOGITS
     EconPapers
    0.49
    UnusedPrivate
    0.49
     HasFactory
    0.47
    ToBounds
    0.46
     antidesliz
    0.44
    员
    0.43
     فريبيس
    0.43
     Beſ
    0.42
    StandardCharsets
    0.42
    aneous
    0.41
    Activations Density 0.487%

    No Known Activations