© 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 EvalsExportsinterp-engineNEWAPI 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. 7076
    Prev
    Next
    INDEX
    Explanations

    programming and code structure elements, specifically focusing on function definitions, returns, and control flow statements

    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
    Personendaten
    -0.50
    Personensuche
    -0.50
    RenderAtEndOf
    -0.47
    /**
    -0.44
    boots
    -0.44
    bridges
    -0.43
    Bootstrap
    -0.43
    boot
    -0.43
    Boots
    -0.43
    Boiler
    -0.42
    POSITIVE LOGITS
     B
    2.63
     b
    2.33
    B
    1.88
     getB
    1.63
     ب
    1.53
    b
    1.45
    getB
    1.41
     Б
    1.30
     б
    1.20
     ब
    1.17
    Activations Density 0.758%

    No Known Activations