© 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. 31-GEMMASCOPE-RES-16K
    11. 555
    Prev
    Next
    INDEX
    Explanations

    code-related syntax and annotations

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

    code comments and license headers in source files.

    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
     žem
    -0.35
    地
    -0.32
    做
    -0.29
     devoir
    -0.29
     løpet
    -0.28
    مانی
    -0.28
    ↵
    -0.28
    ตรี
    -0.28
     blitt
    -0.27
     blevet
    -0.27
    POSITIVE LOGITS
     Roskov
    1.47
    parsedMessage
    1.14
     kasarigan
    1.11
    InjectAttribute
    1.09
     noDo
    1.05
    Diweddarwch
    1.05
    rawDesc
    1.05
     Chwiliwch
    1.02
     ffilmiau
    1.02
     ModelExpression
    1.01
    Activations Density 0.528%

    No Known Activations