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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 14404
    Prev
    Next
    INDEX
    Explanations

    paragraphs about introspection and memory triggered by an event or situation, or about feeling emotions

    oai_token-act-pair · gemini-2.0-flash

    Old English texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     (
    -0.51
     «
    -0.44
     is
    -0.44
    ↵
    -0.44
    .
    -0.43
    <eos>
    -0.42
     I
    -0.41
    ,
    -0.40
     Affaires
    -0.39
    ch
    -0.39
    POSITIVE LOGITS
     Jefus
    1.05
     myſelf
    1.03
    AndEndTag
    0.99
     Theſe
    0.98
     itſelf
    0.98
     Efq
    0.96
     Cæsar
    0.93
     themſelves
    0.92
     himſelf
    0.91
     Chriftian
    0.88
    Activations Density 2.241%

    No Known Activations