© 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. 14823
    Prev
    Next
    INDEX
    Explanations

    references to specific substances and their effects related to health and medicine

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

    followed by prepositions or relation words

    np_acts-logits-general · gemini-2.0-flash

    against or compared to

    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
    \{\\
    -0.72
    NameInMap
    -0.70
    
    -0.69
     Мексичка
    -0.67
    ✨:
    -0.66
    "}")
    -0.63
    OGND
    -0.59
     jspb
    -0.59
     ویکی‌پدیای
    -0.59
    atrician
    -0.59
    POSITIVE LOGITS
     asupra
    0.72
     against
    0.64
     terhadap
    0.64
     towards
    0.63
     toward
    0.58
     versus
    0.57
     compared
    0.57
    RenderAtEndOf
    0.56
     نسبت
    0.54
     đối
    0.54
    Activations Density 0.694%

    No Known Activations