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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 53390
    Prev
    Next
    INDEX
    Explanations

    imports related to utility functions in programming

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

    Java imports and programming constructs

    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
     esk
    -0.56
     виправивши
    -0.54
    Applet
    -0.54
    resave
    -0.54
     beginnetje
    -0.53
     privada
    -0.52
    bindParam
    -0.50
    Diwedd
    -0.49
    éndolo
    -0.49
    SourceChecksum
    -0.47
    POSITIVE LOGITS
     MainAxisSize
    0.65
    AnchorStyles
    0.61
    gorithm
    0.55
    NUMX
    0.54
    databind
    0.53
    StandardCharsets
    0.52
    RectangleBorder
    0.52
    ValueGeneration
    0.50
     Faker
    0.49
    PYX
    0.49
    Activations Density 0.002%

    No Known Activations