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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 4-GEMMASCOPE-TRANSCODER-16K
    4. 13690
    Prev
    Next
    INDEX
    Explanations

    verbs suggesting that someone or something *caused* someone to have a feeling, thought, or insight

    oai_token-act-pair · gemini-2.0-flash

    Causation and influence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     endfor
    -0.59
    tonsoft
    -0.57
    +:+
    -0.55
    ArgsConstructor
    -0.54
    richlet
    -0.53
     exud
    -0.53
     PhpStorm
    -0.53
    iseite
    -0.52
     RSSSF
    -0.51
     excre
    -0.50
    POSITIVE LOGITS
     متعلقه
    0.71
    <bos>
    0.65
    Всем
    0.57
    IonicModule
    0.54
     Référence
    0.52
    CGRectMake
    0.50
    thâu
    0.50
     autorytatywna
    0.50
     menambah
    0.49
    ’
    0.48
    Activations Density 1.125%

    No Known Activations