© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 5796
    Prev
    Next
    INDEX
    Explanations

    data related to research publications and their collaborative authorship patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Counts or quantities

    np_acts-logits-general · gemini-2.0-flash

    number of occurrences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Möglich
    -0.28
     apart
    -0.27
     can
    -0.27
     element
    -0.27
     quite
    -0.26
     or
    -0.25
    łecz
    -0.25
    很
    -0.25
     an
    -0.24
     Should
    -0.24
    POSITIVE LOGITS
     registrations
    0.82
    ſelves
    0.75
     Anzahl
    0.75
     arrests
    0.74
     pregnancies
    0.72
     suicides
    0.71
    parsedMessage
    0.71
     births
    0.71
     aantal
    0.70
     deaths
    0.69
    Activations Density 0.840%

    No Known Activations