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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 4235
    Prev
    Next
    INDEX
    Explanations

    elements related to mathematical calculations and numeric expressions

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

    mathematical expressions and numeric calculations.

    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
     AppCompatTheme
    -0.54
    findpost
    -0.52
     Numerade
    -0.47
    ClInclude
    -0.46
    (!__
    -0.44
    windowFixed
    -0.44
    UrlResolution
    -0.44
    ьаж
    -0.43
    发表于
    -0.43
    原始内容存档于
    -0.42
    POSITIVE LOGITS
     digit
    1.04
    Digit
    0.92
     digits
    0.91
    digit
    0.90
     Digit
    0.90
    digits
    0.80
    Digits
    0.78
     DIGIT
    0.78
     díg
    0.74
     tens
    0.67
    Activations Density 1.131%

    No Known Activations