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 - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 360
    Prev
    Next
    INDEX
    Explanations

    various types of commas and semi-colons that indicate pauses or separations in complex sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CloseOperation
    -0.60
    makeConstraints
    -0.57
    ConstraintMaker
    -0.56
     incentiv
    -0.56
    CodedInputStream
    -0.55
    Rujuakan
    -0.54
     kinda
    -0.54
     ideally
    -0.52
    JNIEnv
    -0.49
    Иск
    -0.49
    POSITIVE LOGITS
     and
    0.60
     AssemblyCulture
    0.60
     bæ
    0.58
     EconPapers
    0.58
     because
    0.57
     ибо
    0.56
    Література
    0.56
    Bearing
    0.51
     فريبيس
    0.50
     —
    0.50
    Activations Density 0.327%

    No Known Activations