Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 14554
    Prev
    Next
    INDEX
    Explanations

    references to toxic substances and environmental contaminants

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

    Pollution and contaminants

    np_acts-logits-general · gemini-2.0-flash

    contaminants, toxicological, exposure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    πά
    -0.32
     sm
    -0.32
    цездатний
    -0.30
    OB
    -0.30
    ud
    -0.30
    oa̍t
    -0.29
    υτό
    -0.29
    WithFormat
    -0.28
     semangat
    -0.28
     ور
    -0.28
    POSITIVE LOGITS
    RegressionTest
    0.72
     myſelf
    0.69
     Houſe
    0.69
     Perſ
    0.67
     contamination
    0.67
     toxicological
    0.66
     ſch
    0.65
     contaminants
    0.65
     ſur
    0.65
     Diſ
    0.65
    Activations Density 0.390%

    No Known Activations