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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 8-GEMMASCOPE-TRANSCODER-16K
    4. 741
    Prev
    Next
    INDEX
    Explanations

    phrases indicating agreement or support within arguments, including references to previous research or legal statutes.

    oai_token-act-pair · gemini-2.0-flash

    agreement, alignment, or comparison

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    MigrationBuilder
    -0.81
    SequentialGroup
    -0.68
     EconPapers
    -0.67
    ukone
    -0.65
     iſt
    -0.61
    LookAnd
    -0.61
     ſch
    -0.61
    ſelf
    -0.59
    GeneratedCode
    -0.58
    CGRectMake
    -0.57
    POSITIVE LOGITS
     TextInputType
    0.50
     Exacts
    0.44
     parada
    0.43
     fre
    0.41
     HEY
    0.41
     обо
    0.41
     InputDecoration
    0.41
     efek
    0.40
    CardContent
    0.40
     IERC
    0.40
    Activations Density 29.075%

    No Known Activations