© 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. 6369
    Prev
    Next
    INDEX
    Explanations

    names of individuals and places

    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
    ValueStyle
    -0.76
    setVerticalGroup
    -0.72
    ThroughAttribute
    -0.61
     Infórmanos
    -0.61
    WriteBarrier
    -0.59
    DeleteBehavior
    -0.55
    awtextra
    -0.54
    urlencoded
    -0.54
     فريبيس
    -0.50
     Italijani
    -0.49
    POSITIVE LOGITS
     PDR
    0.49
    isNullOrEmpty
    0.44
    istani
    0.42
    lotl
    0.39
    lysm
    0.39
     DCT
    0.39
    ktör
    0.39
     professionals
    0.39
     getP
    0.39
    ock
    0.38
    Activations Density 1.321%

    No Known Activations