© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 34-GEMMASCOPE-RES-16K
    11. 6055
    Prev
    Next
    INDEX
    Explanations

    pieces of code or function definitions within programming-related text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LookAnd
    -0.52
     ujednoznacz
    -0.47
    ExtendWith
    -0.47
    bootstrapcdn
    -0.44
    SizeF
    -0.43
     unknownFields
    -0.42
     <>",
    -0.42
    WaitGroup
    -0.42
    EndContext
    -0.42
    ✨:
    -0.41
    POSITIVE LOGITS
     lines
    3.73
     Lines
    3.20
     line
    3.17
    Lines
    2.91
    lines
    2.88
     LINES
    2.78
     Line
    2.61
     líneas
    2.53
     lignes
    2.41
    Line
    2.38
    Activations Density 0.906%

    No Known Activations