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. 7038
    Prev
    Next
    INDEX
    Explanations

    words related to official statements and changing stories

    oai_token-act-pair · gemini-2.0-flash

    story

    np_max-act · 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
    <bos>
    -0.86
    tvguidetime
    -0.52
    NameInMap
    -0.47
    HtmlAttribute
    -0.45
    hibernate
    -0.44
    IBOutlet
    -0.44
    bigliamento
    -0.44
    achuca
    -0.44
    /*++
    -0.43
    +]
    -0.43
    POSITIVE LOGITS
     <=",
    0.80
    +#+#
    0.66
    ExtendWith
    0.63
    Personensuche
    0.60
    ]--;
    0.59
     gradova
    0.58
    makeText
    0.57
    contentLoaded
    0.56
     HasFactory
    0.56
    IonicModule
    0.55
    Activations Density 2.271%

    No Known Activations