© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 19-GEMMASCOPE-RES-16K
    11. 3271
    Prev
    Next
    INDEX
    Explanations

    concessive phrases and expressions of uncertainty or hesitation

    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
    Hentet
    -0.52
     hivyo
    -0.48
     Etrus
    -0.46
    vois
    -0.45
    ysy
    -0.44
    joba
    -0.43
     chande
    -0.43
     AssemblyProduct
    -0.42
     Upan
    -0.42
     thereby
    -0.42
    POSITIVE LOGITS
    richTextPanel
    0.78
     BoxDecoration
    0.74
     AssemblyCulture
    0.71
    errHandler
    0.66
     excuse
    0.65
    __*/
    0.64
    ReusableCell
    0.64
    featureID
    0.64
    tagHelperRunner
    0.63
    KommentareTeilen
    0.63
    Activations Density 0.062%

    No Known Activations