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. 4140
    Prev
    Next
    INDEX
    Explanations

    actions and events related to movement and capacity involving vehicles or transportation

    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
     itſelf
    -0.74
     juſ
    -0.71
     Reſ
    -0.71
     Eſ
    -0.70
     purpoſe
    -0.70
     uſe
    -0.69
     Houſe
    -0.69
     houſe
    -0.68
     urso
    -0.68
    ſelf
    -0.67
    POSITIVE LOGITS
     passenger
    1.09
     passengers
    1.08
    passenger
    0.91
     Passengers
    0.90
     Passenger
    0.87
    Passenger
    0.85
    Passengers
    0.84
     passagers
    0.82
    passengers
    0.80
     penumpang
    0.76
    Activations Density 0.233%

    No Known Activations