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 - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 52945
    Prev
    Next
    INDEX
    Explanations

    HTML document structure and elements

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

    HTML doctype and tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CallOverrides
    -0.70
    IsContent
    -0.65
    tonode
    -0.65
     ProductService
    -0.63
     Recur
    -0.63
    oneofs
    -0.61
    saga
    -0.61
    CppCodeGen
    -0.61
    amaño
    -0.60
     luggage
    -0.60
    POSITIVE LOGITS
    DOCTYPE
    0.76
    defer
    0.46
    abank
    0.46
    yntaxException
    0.43
    CTYPE
    0.43
     hela
    0.42
    orianCalendar
    0.42
    minlength
    0.40
     secured
    0.40
    meen
    0.40
    Activations Density 0.009%

    No Known Activations