© 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. 20-GEMMASCOPE-RES-16K
    11. 14385
    Prev
    Next
    INDEX
    Explanations

    budgetary terms and discussions around fiscal policy and spending cuts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.37
    avadoc
    -0.34
    >);
    -0.32
    Примітки
    -0.32
     
    -0.31
    UnitId
    -0.30
    hfill
    -0.30
     transférez
    -0.30
     língua
    -0.30
     lenker
    -0.29
    POSITIVE LOGITS
    ArrowToggle
    0.67
    UnsafeEnabled
    0.57
     Sacrifice
    0.56
     sacrifice
    0.55
     sacrifices
    0.54
     reductions
    0.54
     Squeeze
    0.52
     Sacrific
    0.52
     trims
    0.49
     shedding
    0.49
    Activations Density 0.195%

    No Known Activations