© 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. 1-GEMMASCOPE-RES-16K
    11. 3863
    Prev
    Next
    INDEX
    Explanations

    instances of the string "ja" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    뀜
    -0.56
     miniaturka
    -0.52
     snippetHide
    -0.48
     HasFactory
    -0.47
    gründ
    -0.46
     onderhoud
    -0.45
    ManagedBean
    -0.45
     vermogen
    -0.45
    hdashline
    -0.45
    quido
    -0.44
    POSITIVE LOGITS
    ja
    0.71
     Ja
    0.69
     ja
    0.69
    Ja
    0.63
     je
    0.57
     assess
    0.53
     estimated
    0.53
    JA
    0.52
     estimate
    0.52
     escape
    0.51
    Activations Density 0.219%

    No Known Activations