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. 7-GEMMASCOPE-TRANSCODER-16K
    4. 7015
    Prev
    Next
    INDEX
    Explanations

    domain-specific terms from scientific and political contexts, possibly related to governmental entities

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     BorderSide
    -0.54
    InputBorder
    -0.51
    互联网档案馆
    -0.49
    vignon
    -0.48
    HasAnnotation
    -0.47
    diction
    -0.47
    UnknownFieldSet
    -0.47
    ropolitan
    -0.46
    fog
    -0.46
    /**
    -0.46
    POSITIVE LOGITS
    ContentAsync
    0.65
     كومونز
    0.61
     mourut
    0.59
    FirstResponder
    0.57
     Normdatei
    0.56
     CreateTagHelper
    0.55
     fallu
    0.52
     geslacht
    0.52
     debout
    0.51
    Cordialement
    0.50
    Activations Density 23.012%

    No Known Activations