© 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-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 15308
    Prev
    Next
    INDEX
    Explanations

    structured data elements and types in programming or markup language contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    //
    -0.56
     createStore
    -0.54
    DoubleQuotes
    -0.52
    vera
    -0.50
    áh
    -0.50
    WEBPACK
    -0.50
    styleType
    -0.49
    parsedMessage
    -0.49
    ensible
    -0.47
     Qa
    -0.46
    POSITIVE LOGITS
    öszi
    0.73
     poule
    0.72
    الدراسه
    0.70
    anskje
    0.65
    PMID
    0.61
    libs
    0.60
     саны
    0.60
     dept
    0.59
     Paglinawan
    0.59
    iella
    0.58
    Activations Density 0.905%

    No Known Activations