© 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. 33-GEMMASCOPE-RES-16K
    6. 11127
    Prev
    Next
    INDEX
    Explanations

    terms associated with safety, privacy, and efficiency in technology and healthcare contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gig
    -0.38
     Chwiliwch
    -0.36
     виправивши
    -0.34
    Publié
    -0.33
    verkehr
    -0.33
    fahrzeug
    -0.31
    sweise
    -0.31
    RTDA
    -0.31
    <>
    -0.31
    artigen
    -0.31
    POSITIVE LOGITS
     issues
    0.93
     improvements
    0.86
     concerns
    0.85
     considerations
    0.83
     improvement
    0.82
    concerns
    0.80
     ISSUES
    0.80
     Issues
    0.77
    issues
    0.77
     Concerns
    0.74
    Activations Density 0.995%

    No Known Activations