© 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. 155
    Prev
    Next
    INDEX
    Explanations

    medical terminology and concepts related to health conditions

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

    Negation or prevention of an action

    np_acts-logits-general · gemini-2.0-flash

    prevent or reduce undesirable events

    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
     незавершена
    -0.58
     ComVisible
    -0.58
     AssemblyProduct
    -0.56
    UrlResolution
    -0.56
     silenced
    -0.54
     genomen
    -0.54
     Disabled
    -0.52
    romole
    -0.52
     caché
    -0.52
     undisturbed
    -0.51
    POSITIVE LOGITS
     tendency
    0.76
     tende
    0.70
     leaks
    0.68
     leaking
    0.66
     prone
    0.65
     leak
    0.64
     tend
    0.61
     sometimes
    0.61
     excessively
    0.60
    endency
    0.60
    Activations Density 0.495%

    No Known Activations