© 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. 24-GEMMASCOPE-RES-16K
    11. 1961
    Prev
    Next
    INDEX
    Explanations

    specific geographical or administrative entities and their locations

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

    Geographic place names

    np_acts-logits-general · gemini-2.0-flash

    place names or locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     utafitiHapana
    -0.68
    SourceChecksum
    -0.63
    Manbalar
    -0.60
     مشين
    -0.59
    Билгалдахарш
    -0.54
    queryInterface
    -0.53
    GEBURTSDATUM
    -0.48
     kaarangay
    -0.48
     թվական
    -0.48
    NameInMap
    -0.48
    POSITIVE LOGITS
    etcode
    0.58
    ivasan
    0.58
    rogels
    0.57
    forRoot
    0.57
     overlying
    0.57
    etCode
    0.56
     altitudes
    0.56
    urnum
    0.55
     confluence
    0.54
     Parigi
    0.54
    Activations Density 0.142%

    No Known Activations