© 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. 10387
    Prev
    Next
    INDEX
    Explanations

    expressions related to variable assignments and comparisons in code

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

    loop comparison operators and loop boundary values in for loops.

    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
     yym
    -0.43
     DET
    -0.42
    EUR
    -0.40
    bourhood
    -0.40
    rimer
    -0.40
     Lynch
    -0.39
    strto
    -0.39
     metabolic
    -0.39
     Ep
    -0.39
    一楼
    -0.39
    POSITIVE LOGITS
    脚注の使い方
    0.61
     nakalista
    0.57
    AndEndTag
    0.57
    Diweddarwch
    0.55
     EconPapers
    0.53
     ExecuteAsync
    0.50
    principalColumn
    0.49
     excepto
    0.49
     moindre
    0.49
     Meksiku
    0.49
    Activations Density 0.192%

    No Known Activations