© 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. 31-GEMMASCOPE-RES-16K
    11. 13945
    Prev
    Next
    INDEX
    Explanations

    key terms related to legal agreements and intellectual property

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    visual elements being layered or overlaid on top of other elements.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ChildScrollView
    -0.49
    énario
    -0.38
    تقاوى
    -0.34
    المشاركات
    -0.31
    новништво
    -0.31
    openSession
    -0.30
    AndEndTag
    -0.30
    ParallelGroup
    -0.30
     Broad
    -0.29
     useNavigate
    -0.29
    POSITIVE LOGITS
     overlay
    1.55
     overlays
    1.39
     Overlay
    1.34
     overlaid
    1.32
     superimposed
    1.23
    Overlay
    1.13
    overlay
    1.10
     overlapping
    1.07
     overlapped
    1.05
     transparency
    1.01
    Activations Density 0.466%

    No Known Activations