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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 19-GEMMASCOPE-TRANSCODER-16K
    4. 6915
    Prev
    Next
    INDEX
    Explanations

    German sentences containing references to modal verbs and grammatical constructs.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     minne
    -0.56
     once
    -0.54
     properly
    -0.53
     InputDecoration
    -0.51
    ByExample
    -0.51
     keenly
    -0.49
     also
    -0.48
    ItemBackground
    -0.48
    FieldBuilder
    -0.48
     instinctively
    -0.48
    POSITIVE LOGITS
     createSprite
    0.57
     CreateTagHelper
    0.57
    ReusableCell
    0.55
    yelitis
    0.54
     zufolge
    0.53
    Välislingid
    0.52
     Kroger
    0.50
    tagHelperRunner
    0.49
     JpaRepository
    0.48
     Bourgoin
    0.48
    Activations Density 0.431%

    No Known Activations