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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 18-GEMMASCOPE-RES-16K
    6. 608
    Prev
    Next
    INDEX
    Explanations

    mentions of meetings and events held in specific locations

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

    Locations like rooms, buildings, and centers

    np_acts-logits-general · gemini-2.0-flash

    places like rooms and buildings

    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
    TouchListener
    -0.50
    cop
    -0.49
    кипа
    -0.49
     sauvage
    -0.48
     noDo
    -0.47
    getic
    -0.47
     quotidi
    -0.47
    dataset
    -0.47
    ียว
    -0.45
     policiais
    -0.45
    POSITIVE LOGITS
     auditorium
    1.21
     room
    1.16
     rooms
    1.12
     hall
    1.07
     Room
    1.06
     Auditorium
    1.04
     Rooms
    0.99
    Room
    0.98
     ROOM
    0.97
     salle
    0.97
    Activations Density 0.180%

    No Known Activations