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. 19-GEMMASCOPE-TRANSCODER-16K
    4. 10395
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns with the theme of ownership of something, by a person or group of people

    oai_token-act-pair · gemini-2.0-flash

    possessive doing something

    np_max-act-logits · 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
    ADVERTISEMENT
    -0.57
    secon
    -0.54
    indole
    -0.54
     duplication
    -0.54
    ÍTULO
    -0.54
    कर्
    -0.53
    Enllaces
    -0.53
     ORGANISM
    -0.50
     resourceCulture
    -0.50
     emulsion
    -0.50
    POSITIVE LOGITS
    AddTagHelper
    0.68
     preuves
    0.67
     vérit
    0.67
     relatifs
    0.56
    ეთ
    0.54
    principalColumn
    0.54
     lumières
    0.52
    醐
    0.51
     تانيه
    0.51
    TestingModule
    0.51
    Activations Density 0.487%

    No Known Activations