© 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. 31-GEMMASCOPE-RES-16K
    11. 16082
    Prev
    Next
    INDEX
    Explanations

    concerns about privacy and measures to protect against surveillance

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

    discussions about covering or protecting webcams and cameras with physical barriers like tape.

    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
     <<<<<<<<<<<<<<
    -0.63
    OGND
    -0.57
    
    -0.55
    bibitem
    -0.53
    SequentialGroup
    -0.50
     suela
    -0.49
    newtheorem
    -0.49
    principalTable
    -0.48
     informée
    -0.46
    RegistryLite
    -0.46
    POSITIVE LOGITS
     covering
    1.68
     Covering
    1.57
     cover
    1.54
    Cover
    1.46
     covered
    1.44
     covers
    1.41
     Cover
    1.38
     COVER
    1.38
    covering
    1.35
    cover
    1.28
    Activations Density 0.542%

    No Known Activations