Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3240
    Prev
    Next
    INDEX
    Explanations

    structural or syntactic elements in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Swift/Scala code, structs, and extensions

    np_acts-logits-general · gemini-2.0-flash

    code constructs and documentation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     defaultstate
    -0.87
    enumii
    -0.73
    featureID
    -0.72
     resourceCulture
    -0.69
    ɵɵelementStart
    -0.69
    ConstraintMaker
    -0.68
     initComponents
    -0.68
     protoimpl
    -0.67
    awtextra
    -0.66
    CopyWith
    -0.66
    POSITIVE LOGITS
    extension
    0.62
     extension
    0.58
    struct
    0.55
     scala
    0.52
     print
    0.50
     extensions
    0.49
    protocol
    0.48
     extend
    0.47
     Eilish
    0.45
     protocol
    0.45
    Activations Density 0.087%

    No Known Activations