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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 7688
    Prev
    Next
    INDEX
    Explanations

    terms related to anabolic steroids and their effects in sports and bodybuilding contexts

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

    exercise, drugs, and relationships

    np_acts-logits-general · gemini-2.0-flash

    performance-enhancing drugs

    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
     initComponents
    -0.69
    IBOutlet
    -0.59
    MigrationBuilder
    -0.57
    ctia
    -0.55
    ERÍA
    -0.54
    Esper
    -0.52
    WriteLiteral
    -0.51
     COMERC
    -0.50
     télécommande
    -0.50
     charms
    -0.49
    POSITIVE LOGITS
     training
    1.12
    Training
    1.00
     Training
    1.00
    training
    0.96
     TRAINING
    0.90
     bodybuilding
    0.85
    TRAINING
    0.85
    Train
    0.78
     recovery
    0.78
     workouts
    0.78
    Activations Density 0.128%

    No Known Activations