© 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. 15-GEMMASCOPE-RES-16K
    11. 7201
    Prev
    Next
    INDEX
    Explanations

    structured data and its associated attributes in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ########.
    -0.98
    UserScript
    -0.87
    StructEnd
    -0.81
    uxxxx
    -0.75
    ponses
    -0.74
     Himo
    -0.73
     Réponses
    -0.73
    itinéraire
    -0.72
     estimés
    -0.70
     Roskov
    -0.68
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.68
    EndContext
    0.55
     unknownFields
    0.53
    tagHelper
    0.51
     transfieras
    0.49
    AndroidJUnit
    0.49
     فريبيس
    0.47
    LikeLike
    0.47
     mergeFrom
    0.47
    PYX
    0.47
    Activations Density 0.369%

    No Known Activations