© 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. 12594
    Prev
    Next
    INDEX
    Explanations

    terms related to molecular biology and biochemical processes

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

    ending with "eg" or starting with "neg"

    np_acts-logits-general · gemini-2.0-flash

    segregate, argues, assignables, magick, egocentric, negligent

    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
    ski
    -0.84
    sho
    -0.83
    s
    -0.83
    shire
    -0.82
    sing
    -0.81
    arithmic
    -0.81
    stein
    -0.80
    ova
    -0.78
    spa
    -0.78
    sau
    -0.77
    POSITIVE LOGITS
    й
    0.57
    ي
    0.47
     للمعارف
    0.45
    AuthContext
    0.45
    k
    0.43
    ‌ای
    0.43
     larmes
    0.43
     réaction
    0.42
    NewGuid
    0.42
    SequentialGroup
    0.42
    Activations Density 0.430%

    No Known Activations