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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 106258
    Prev
    Next
    INDEX
    Explanations

    mentions of slots and their configurations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     Be
    -0.54
     E
    -0.50
     Re
    -0.49
     New
    -0.47
     A
    -0.45
     Che
    -0.45
     M
    -0.45
    }}}\
    -0.45
     Y
    -0.45
    }}-\
    -0.43
    POSITIVE LOGITS
     Slot
    1.20
    slot
    1.16
     slot
    1.15
     SLOT
    1.12
    Slot
    1.05
    slots
    1.02
     Slots
    0.99
    SLOT
    0.98
     slots
    0.96
    Slots
    0.91
    Activations Density 0.004%

    No Known Activations