© 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. 20-GEMMASCOPE-RES-16K
    11. 8072
    Prev
    Next
    INDEX
    Explanations

    terms related to mental health and societal issues

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

    Followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    who, which, I, we + verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     geweest
    -0.56
    ftagPool
    -0.53
     داشته
    -0.53
     disponibilités
    -0.52
    ModelSerializer
    -0.50
    XtraEditors
    -0.49
    IContainer
    -0.48
    loroethane
    -0.48
    rxjs
    -0.47
    datatables
    -0.47
    POSITIVE LOGITS
     hadn
    0.73
     became
    0.70
     оказалось
    0.62
     decided
    0.61
     bleek
    0.60
    OGND
    0.60
     okaza
    0.60
     Meksiku
    0.58
     متعلقه
    0.56
     ternyata
    0.54
    Activations Density 0.416%

    No Known Activations