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

    Neuronpedia

    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. 30-GEMMASCOPE-RES-16K
    11. 12464
    Prev
    Next
    INDEX
    Explanations

    action-related terms, particularly those associated with buying or taking

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

    Follows "take," "make," or "buy"

    np_acts-logits-general · gemini-2.0-flash

    take away, takeoffs, make-up, Buy Now

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    @[+][
    -0.41
     excise
    -0.36
    LETED
    -0.35
     genomen
    -0.34
    literals
    -0.34
    Brien
    -0.34
     удалить
    -0.34
     amminist
    -0.32
     genommen
    -0.32
    Rujuakan
    -0.32
    POSITIVE LOGITS
    setVerticalGroup
    0.71
     surla
    0.64
    rungsseite
    0.58
     onOptions
    0.57
     ujednoznacz
    0.57
     يتيمه
    0.56
    SourceChecksum
    0.55
    LookAnd
    0.53
     offs
    0.52
     insuffisamment
    0.52
    Activations Density 0.525%

    No Known Activations