© 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. 0-GEMMASCOPE-RES-16K
    11. 12050
    Prev
    Next
    INDEX
    Explanations

    references to a specific term or abbreviation, likely related to a structural or functional aspect in a certain field

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     estekak
    -0.74
    Datuak
    -0.73
    parsedMessage
    -0.72
     Numerade
    -0.66
     informée
    -0.64
     AssemblyCulture
    -0.64
    __*/
    -0.64
     chi̍t
    -0.63
     tartalomajánló
    -0.63
     Taktlose
    -0.63
    POSITIVE LOGITS
     relation
    0.79
     formats
    0.65
     format
    0.63
     dd
    0.62
    dd
    0.61
     DD
    0.58
     phrase
    0.57
    DD
    0.57
     element
    0.56
    relation
    0.55
    Activations Density 0.177%

    No Known Activations