© 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. 18-GEMMASCOPE-RES-16K
    6. 2533
    Prev
    Next
    INDEX
    Explanations

    references to specific places or facilities

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

    Locations with names like "[Word] [Place type]"

    np_acts-logits-general · gemini-2.0-flash

    place names and types of locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Normdatei
    -0.92
     kasarigan
    -0.92
     nahilalakip
    -0.87
    
    -0.85
    RenderAtEndOf
    -0.82
     autorytatywna
    -0.78
     تانيه
    -0.78
    protoimpl
    -0.77
    ValueStyle
    -0.72
    ThroughAttribute
    -0.72
    POSITIVE LOGITS
    seamnă
    0.64
     atrium
    0.55
     viață
    0.55
     ſtate
    0.54
     centers
    0.53
     condos
    0.52
     ftate
    0.52
     willows
    0.52
     cedar
    0.52
     oaks
    0.51
    Activations Density 0.117%

    No Known Activations