© 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-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 1190
    Prev
    Next
    INDEX
    Explanations

    references to specific data structures and programming constructs, particularly in a coding context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    djangoproject
    -0.58
    parsedMessage
    -0.56
     Roskov
    -0.54
    цездатний
    -0.53
     Réponses
    -0.53
     ostavi
    -0.52
    vaadin
    -0.50
    GEBURTS
    -0.49
     dice
    -0.49
    StructEnd
    -0.49
    POSITIVE LOGITS
     backing
    0.76
     Rape
    0.76
     Backing
    0.73
    Backing
    0.65
     rape
    0.65
    ruptedException
    0.64
    putExtra
    0.63
     backed
    0.63
    Rape
    0.61
     للمعارف
    0.61
    Activations Density 0.818%

    No Known Activations