© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 8229
    Prev
    Next
    INDEX
    Explanations

    medical conditions related to pregnancy and their implications

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

    Mathematical and scientific notation

    np_acts-logits-general · gemini-2.0-flash

    specifying context after comma or specific words

    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
     boroughs
    -0.70
    ükemmel
    -0.66
    moveToFirst
    -0.64
    etcode
    -0.63
     AppComponent
    -0.61
     microm
    -0.61
    bersicht
    -0.60
     prophylactic
    -0.58
    AXI
    -0.57
     summers
    -0.57
    POSITIVE LOGITS
    Datuak
    0.51
    UnusedPrivate
    0.49
     kla
    0.45
     cuk
    0.45
     lont
    0.45
    verwijspagina
    0.45
     akad
    0.43
    Parcelize
    0.43
    ेशा
    0.42
    FTS
    0.41
    Activations Density 0.118%

    No Known Activations