© 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-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 15200
    Prev
    Next
    INDEX
    Explanations

    phrases related to educational guidance and student support services

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

    Canadian locations and entities

    np_acts-logits-general · gemini-2.0-flash

    Canadian places and arts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    asInstanceOf
    -0.72
    Neighbors
    -0.60
     flavorful
    -0.59
     labor
    -0.59
     flavors
    -0.57
    theater
    -0.57
     theater
    -0.56
    новништво
    -0.56
    favorite
    -0.55
     américaine
    -0.55
    POSITIVE LOGITS
     Canadians
    1.22
     Canada
    1.22
     Toronto
    1.18
     Canadian
    1.17
     honour
    1.14
     Edmonton
    1.14
    Canada
    1.13
     Ontario
    1.13
     Ottawa
    1.12
     Winnipeg
    1.11
    Activations Density 0.303%

    No Known Activations