Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 4257
    Prev
    Next
    INDEX
    Explanations

    situations involving police chases and traffic violations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PasswordEncoder
    -0.61
    ISupport
    -0.57
    Kariera
    -0.56
    ⌋
    -0.50
     viewType
    -0.49
     Walkover
    -0.49
    getOutputStream
    -0.48
    stø
    -0.48
     plads
    -0.48
     saites
    -0.48
    POSITIVE LOGITS
     driving
    1.03
     Driving
    1.01
     drivers
    0.97
     traffic
    0.93
    Driving
    0.93
     motorists
    0.92
     Drivers
    0.91
     highway
    0.89
     Traffic
    0.88
     driver
    0.88
    Activations Density 0.245%

    No Known Activations