© 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-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 9006
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions involving fractions

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

    Fractions in LaTeX formulas

    np_acts-logits-general · gemini-2.0-flash

    latex fractions and mathematical expressions

    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
    IsMutable
    -0.64
     kasarigan
    -0.58
     encomp
    -0.58
     audi
    -0.52
     kombat
    -0.50
    AndEndTag
    -0.50
    دانشنامهٔ
    -0.50
     exemp
    -0.48
     Audit
    -0.46
    PerformLayout
    -0.46
    POSITIVE LOGITS
    frac
    1.63
    dfrac
    1.38
    mfrac
    1.03
    tfrac
    0.98
     frac
    0.90
    Frac
    0.67
     Fraction
    0.63
     fraction
    0.60
    stackrel
    0.59
    Fraction
    0.59
    Activations Density 0.364%

    No Known Activations