© 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. 33-GEMMASCOPE-RES-16K
    11. 5239
    Prev
    Next
    INDEX
    Explanations

    programming constructs and elements related to data structures and UI components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inerea
    -0.48
    ONESIA
    -0.46
    Datuak
    -0.45
    yip
    -0.44
    TypedDataSet
    -0.43
    ajur
    -0.43
    zzar
    -0.42
     PIX
    -0.42
    tux
    -0.42
    copic
    -0.42
    POSITIVE LOGITS
     theme
    1.52
     thread
    1.49
     Th
    1.45
     THREAD
    1.40
     Theme
    1.39
     threat
    1.38
     Thread
    1.38
    theme
    1.38
     Threat
    1.35
    Theme
    1.34
    Activations Density 0.349%

    No Known Activations