© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 7297
    Prev
    Next
    INDEX
    Explanations

    guidance and recommendations regarding health precautions

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

    Imperative sentences and instructions

    np_acts-logits-general · gemini-2.0-flash

    please do the action

    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
    OGND
    -0.56
    posedge
    -0.47
    CommandHandler
    -0.46
    Derbyniad
    -0.44
     arbitrary
    -0.43
     intervi
    -0.43
     اوم
    -0.41
    
    -0.41
    개
    -0.40
     getDescription
    -0.40
    POSITIVE LOGITS
     remember
    1.00
     always
    0.97
     consider
    0.93
     Always
    0.92
     beware
    0.91
     ALWAYS
    0.90
     check
    0.88
    Always
    0.87
     Avoid
    0.85
     avoid
    0.84
    Activations Density 0.403%

    No Known Activations