© 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. 40-GEMMASCOPE-RES-16K
    6. 5568
    Prev
    Next
    INDEX
    Explanations

    product features and variations in items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyTitle
    -0.48
     esternos
    -0.43
    órmula
    -0.40
    InitVars
    -0.40
    ISupport
    -0.39
    estrado
    -0.39
    Arrows
    -0.39
     gameState
    -0.38
     prêtres
    -0.38
    Erreferentziak
    -0.38
    POSITIVE LOGITS
     styles
    1.64
     types
    1.63
     varieties
    1.41
     formats
    1.36
     sizes
    1.32
    types
    1.23
     configurations
    1.21
     tipos
    1.20
     flavors
    1.19
     kinds
    1.17
    Activations Density 0.916%

    No Known Activations