© 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. 10447
    Prev
    Next
    INDEX
    Explanations

    terms related to pharmacological effects and receptor interactions

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

    Selective receptor agonists or antagonists

    np_acts-logits-general · gemini-2.0-flash

    selective receptor antagonists

    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
    IntoConstraints
    -0.79
    TypedDataSet
    -0.68
    脚注の使い方
    -0.65
     ComVisible
    -0.63
     hygien
    -0.60
     correspondents
    -0.56
    putstr
    -0.54
    Hygiene
    -0.53
     streaks
    -0.52
     sentin
    -0.52
    POSITIVE LOGITS
     Block
    0.73
     block
    0.72
     blocking
    0.71
    block
    0.71
     inhibition
    0.70
    Block
    0.70
     selective
    0.64
     interact
    0.63
     оригіналу
    0.63
     blockade
    0.62
    Activations Density 1.301%

    No Known Activations