© 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. 9677
    Prev
    Next
    INDEX
    Explanations

    technical elements related to Django models and database operations

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

    Python code and programming syntax elements like imports, class definitions, function calls, and file paths.

    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
     **
    -0.43
    **
    -0.41
     Palmer
    -0.35
    importanza
    -0.33
     كورة
    -0.33
    ,**
    -0.32
    ApplicationTests
    -0.32
     Koss
    -0.31
    medriver
    -0.31
     aun
    -0.31
    POSITIVE LOGITS
     propOrder
    0.68
     فريبيس
    0.60
    PyExc
    0.51
     للمعارف
    0.47
    󠁢
    0.46
     ?>>
    0.45
     @"";
    0.45
    elemField
    0.44
     quæ
    0.43
    Portail
    0.43
    Activations Density 0.208%

    No Known Activations