© 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. 12-GEMMASCOPE-RES-16K
    11. 6932
    Prev
    Next
    INDEX
    Explanations

    phrases related to devices designed for user convenience and functionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ftagPool
    -0.73
    Personensuche
    -0.69
     ModelExpression
    -0.64
    rungsseite
    -0.63
    awtextra
    -0.63
    GEBURTS
    -0.61
    rawDesc
    -0.56
    Personendaten
    -0.54
    AndEndTag
    -0.54
     disambiguazione
    -0.54
    POSITIVE LOGITS
     intended
    0.42
     should
    0.38
    celo
    0.37
    GroupId
    0.37
     designed
    0.37
    gebraucht
    0.36
     meant
    0.35
     ſta
    0.35
     intending
    0.35
     pleaſure
    0.35
    Activations Density 0.580%

    No Known Activations