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. 6981
    Prev
    Next
    INDEX
    Explanations

    pronouns, possessives, and some past tense verbs, with some higher firing for the word 'creation'.

    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
    Datuak
    -0.49
    ppro
    -0.47
     saites
    -0.46
    lu
    -0.46
    his
    -0.45
    ele
    -0.45
    ra
    -0.44
    диа
    -0.43
    mer
    -0.42
    awtextra
    -0.42
    POSITIVE LOGITS
     houſe
    0.78
     Efq
    0.78
     purpoſe
    0.76
     Савезне
    0.75
     themſelves
    0.75
    wiſe
    0.73
     ſmall
    0.70
    ſelf
    0.70
    (;;)
    0.69
     myſelf
    0.68
    Activations Density 1.764%

    No Known Activations