© 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. 18-GEMMASCOPE-RES-16K
    6. 10729
    Prev
    Next
    INDEX
    Explanations

    terms related to environmental issues and crisis

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

    after technical/scientific terms

    np_acts-logits-general · gemini-2.0-flash

    drug resistance and population dynamics

    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
    NOPQRST
    -0.82
    */),
    -0.69
     <=",
    -0.67
    олові
    -0.67
    ">//
    -0.67
    SerializedSize
    -0.66
    ")));
    
    -0.63
    CodedInputStream
    -0.62
    (")");
    -0.62
    twimg
    -0.61
    POSITIVE LOGITS
    CloseOperation
    0.70
     trajets
    0.63
     useParams
    0.61
    HomeAsUpEnabled
    0.60
    省市镇
    0.60
     MaterialApp
    0.56
    WebServlet
    0.55
    PageRoute
    0.55
    Portail
    0.54
     NavController
    0.53
    Activations Density 19.213%

    No Known Activations