© 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. 8944
    Prev
    Next
    INDEX
    Explanations

    structures indicative of code execution or function closures

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

    closing braces and brackets that mark the end of code blocks or data structures.

    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
    ↵
    -0.48
    InjectAttribute
    -0.46
    %"),
    -0.38
     rena
    -0.36
    ruiter
    -0.35
    DotNetBar
    -0.35
     pen
    -0.34
     برانيه
    -0.33
     والع
    -0.33
     ins
    -0.33
    POSITIVE LOGITS
    parsedMessage
    0.54
     surla
    0.51
    Jeografia
    0.49
     незавершена
    0.49
     SwitchCompat
    0.49
    хьтан
    0.46
    ValueGenerated
    0.46
     dAtA
    0.46
    endregion
    0.46
    tagHelperRunner
    0.46
    Activations Density 0.252%

    No Known Activations