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. 14730
    Prev
    Next
    INDEX
    Explanations

    the phrase "growing [noun] of", with a slight preference for scholarly writing

    oai_token-act-pair · gemini-2.0-flash

    body

    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
    ]--;
    -0.54
    IntoConstraints
    -0.52
    HasIndex
    -0.50
    ์
    -0.50
    řízen
    -0.48
    řízení
    -0.47
    ftagPool
    -0.46
    médiaire
    -0.46
     FetchType
    -0.46
    ]='\
    -0.46
    POSITIVE LOGITS
     body
    3.66
    body
    3.13
     Body
    3.09
    Body
    3.02
     bodies
    3.00
     BODY
    2.88
     Bodies
    2.63
    bodies
    2.53
    BODY
    2.48
    Bodies
    2.22
    Activations Density 2.513%

    No Known Activations