© 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 - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 10174
    Prev
    Next
    INDEX
    Explanations

    terms related to exposure and risk assessment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MENAFN
    -0.58
     ainfi
    -0.57
     saveiro
    -0.55
     nė
    -0.55
     resultList
    -0.52
     beslu
    -0.52
     createState
    -0.51
    IVEREF
    -0.51
     wireType
    -0.51
    adaptiveStyles
    -0.50
    POSITIVE LOGITS
     exposure
    1.88
    Exposure
    1.72
     Exposure
    1.70
    exposure
    1.65
     EXPOSURE
    1.59
     exposed
    1.53
     exposures
    1.48
     expose
    1.44
    exposed
    1.42
     exposing
    1.34
    Activations Density 0.226%

    No Known Activations