© 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. 9-GEMMASCOPE-RES-16K
    11. 9966
    Prev
    Next
    INDEX
    Explanations

    occurrences of string manipulation and function definitions in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    migrationBuilder
    -0.68
    AccessorTable
    -0.68
     للمعارف
    -0.65
     المعيارى
    -0.64
    ########.
    -0.63
    ChildScrollView
    -0.60
    principalColumn
    -0.60
     tartalomajánló
    -0.56
    rungsseite
    -0.55
    queryInterface
    -0.54
    POSITIVE LOGITS
     hlad
    0.39
    getAbsolutePath
    0.39
     errorMessage
    0.39
     kartun
    0.38
    tagName
    0.38
     équ
    0.37
    packageName
    0.37
     thẳng
    0.35
    ModuleName
    0.34
     isEqualToString
    0.34
    Activations Density 0.290%

    No Known Activations