© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 13355
    Prev
    Next
    INDEX
    Explanations

    mathematical relationships involving scaling, proportionality, and efficiency in complex systems

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

    This neuron detects mathematical expressions, particularly those containing fractions, ratios, and proportional relationships.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    mathematical expressions and formulas containing variables, operators, and fractions.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Signalez
    -0.39
    ihnachts
    -0.39
    intă
    -0.34
    ApplicationTests
    -0.34
    伍
    -0.33
    minas
    -0.32
    Ground
    -0.32
     intent
    -0.31
    ocarc
    -0.31
     ब्रेकडाउन
    -0.31
    POSITIVE LOGITS
     reciprocal
    0.95
     inverse
    0.83
     Recipro
    0.75
     reciproc
    0.74
     recipro
    0.73
     Inverse
    0.69
     inversely
    0.69
    reci
    0.68
     RECIP
    0.66
    inverse
    0.66
    Activations Density 0.988%

    No Known Activations