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. 7131
    Prev
    Next
    INDEX
    Explanations

    code comments that mention a file being created

    oai_token-act-pair · gemini-2.0-flash

    Created

    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
    aarrggbb
    -0.58
     RVA
    -0.45
    folium
    -0.44
     invokingState
    -0.42
    Normdaten
    -0.42
     ref
    -0.42
    ม
    -0.42
    principalColumn
    -0.41
    ErrUnexpectedEOF
    -0.41
    setVerticalGroup
    -0.41
    POSITIVE LOGITS
    contentLoaded
    0.65
    Personendaten
    0.62
    ="<?=$
    0.58
    unschweig
    0.57
    MemoryWarning
    0.57
     समीक्षाओं
    0.57
    bbene
    0.56
     esternos
    0.56
     оригіналу
    0.56
     Argus
    0.55
    Activations Density 0.290%

    No Known Activations