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. 14457
    Prev
    Next
    INDEX
    Explanations

    questions about requirements for taking an exam specifically related to engineering

    oai_token-act-pair · gemini-2.0-flash

    education/engineering

    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
    GraphicsUnit
    -0.56
    ContentAlignment
    -0.54
    SourceChecksum
    -0.53
    EXPERIMENTAL
    -0.50
    awaiter
    -0.50
    displaymath
    -0.50
    kum
    -0.49
    zeera
    -0.49
     protoimpl
    -0.48
     Harn
    -0.46
    POSITIVE LOGITS
    InstrumentedTest
    0.66
     كومونز
    0.65
    DllImport
    0.64
     voulais
    0.56
    CloseOperation
    0.54
    rrggbb
    0.54
    rhosis
    0.54
    pellier
    0.53
     cleared
    0.52
    atown
    0.52
    Activations Density 0.949%

    No Known Activations