© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 2500
    Prev
    Next
    INDEX
    Explanations

    terms related to biology and medicine, particularly focusing on cellular or physiological processes

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

    starting with "Ble", "Fle", or "Ple"

    np_acts-logits-general · gemini-2.0-flash

    ble, ple, fle, gle prefixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CASA
    -0.72
    Stark
    -0.72
    Tikang
    -0.68
    )}}
    -0.66
    eabouts
    -0.65
     OMITBAD
    -0.65
     Herrick
    -0.65
     Audiodateien
    -0.64
    starch
    -0.63
    /**
    -0.62
    POSITIVE LOGITS
     Leona
    0.99
    LE
    0.93
    le
    0.93
     Merle
    0.91
     lemmas
    0.88
     pleaſure
    0.88
     BLE
    0.88
     Leandro
    0.87
     Lecce
    0.87
     LE
    0.86
    Activations Density 0.316%

    No Known Activations