© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 12659
    Prev
    Next
    INDEX
    Explanations

    contextual references to locations and notable sites

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

    that describe locations or establishments

    np_acts-logits-general · gemini-2.0-flash

    places and entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MethodManager
    -0.68
     housewife
    -0.60
     arşivlendi
    -0.60
    AccessorTable
    -0.55
    HideFlags
    -0.55
    derabad
    -0.54
    parsedMessage
    -0.54
     raincoat
    -0.54
    >{@
    -0.54
     divorce
    -0.53
    POSITIVE LOGITS
     establishments
    1.19
     facilities
    1.16
     places
    1.10
     venues
    1.06
     buildings
    1.04
     institutions
    1.03
     landmarks
    0.99
     structures
    0.95
    facilities
    0.93
     locations
    0.92
    Activations Density 0.267%

    No Known Activations