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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 6974
    Prev
    Next
    INDEX
    Explanations

    comparative phrases that indicate a preference or choice between two options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ViewImports
    -0.56
     Helio
    -0.55
     glab
    -0.53
    FU
    -0.51
    IU
    -0.50
     TextAppearance
    -0.48
     Freeport
    -0.48
    XZ
    -0.47
    UV
    -0.47
    CIL
    -0.47
    POSITIVE LOGITS
     rather
    1.66
     Rather
    1.48
    Rather
    1.48
    rather
    1.46
     piuttosto
    1.17
     plutôt
    1.12
    uttosto
    0.86
    むしろ
    0.79
     raczej
    0.79
     vielmehr
    0.78
    Activations Density 0.174%

    No Known Activations