© 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. 22-GEMMASCOPE-RES-16K
    11. 14525
    Prev
    Next
    INDEX
    Explanations

    chemical compounds and their associated reactions

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

    Fatty acids or chemical acids

    np_acts-logits-general · gemini-2.0-flash

    organic acid names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bege
    -0.50
    RTEE
    -0.48
     Plume
    -0.47
     Phạm
    -0.47
    posedge
    -0.47
     ilma
    -0.46
     Daun
    -0.46
    VIAF
    -0.46
     babys
    -0.45
    ViewFeatures
    -0.45
    POSITIVE LOGITS
     acid
    1.55
     acids
    1.31
     Acid
    1.27
    acid
    1.18
    Acid
    1.13
     ACID
    1.05
     Acids
    1.04
    acide
    1.03
    酸
    1.00
     ácido
    0.98
    Activations Density 0.371%

    No Known Activations