© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 10496
    Prev
    Next
    INDEX
    Explanations

    descriptions of tightness or tension in various contexts

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

    "tight" and its variations

    np_acts-logits-general · gemini-2.0-flash

    tight spot, end, gas, rope, year, loop

    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
    findpost
    -0.92
     تانيه
    -0.78
    GEBURTSDATUM
    -0.73
    الحياه
    -0.70
    enumi
    -0.69
    Portale
    -0.68
     مرئيه
    -0.67
     متعلقه
    -0.66
     betweenstory
    -0.65
    abestanden
    -0.64
    POSITIVE LOGITS
     tight
    1.25
    Tight
    1.17
     Tight
    1.16
     tighter
    1.10
    tight
    1.05
     tighten
    0.92
     tightened
    0.88
     tightly
    0.87
     tightening
    0.87
     tightness
    0.81
    Activations Density 0.133%

    No Known Activations