© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 9334
    Prev
    Next
    INDEX
    Explanations

    mentions of "SC" (possibly referring to a specific scientific term or acronym)

    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
     initialise
    -0.38
     onOptions
    -0.37
     bod
    -0.36
     далее
    -0.36
     Elektron
    -0.36
     QtWidgets
    -0.35
     paga
    -0.35
     arte
    -0.35
     Automat
    -0.35
     propOrder
    -0.34
    POSITIVE LOGITS
    bearing
    0.65
     bearing
    0.65
    Bearing
    0.59
     retrô
    0.57
     celebrating
    0.54
     Bearing
    0.54
     Signalez
    0.54
     carrying
    0.53
     հղումներ
    0.50
     Carrying
    0.50
    Activations Density 0.247%

    No Known Activations