Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 3196
    Prev
    Next
    INDEX
    Explanations

    terms and data related to scientific measurements and experimental results

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

    Isotopes and radioactive elements

    np_acts-logits-general · gemini-2.0-flash

    isotopes and radioactive elements

    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
     saving
    -0.54
     save
    -0.52
    getSystemService
    -0.50
     surla
    -0.49
     Save
    -0.48
    save
    -0.48
    SAVE
    -0.48
     saves
    -0.48
    modb
    -0.47
    Save
    -0.46
    POSITIVE LOGITS
     isotopes
    1.03
     isotope
    1.03
     radioactive
    0.97
     radio
    0.94
    radio
    0.91
     isotopic
    0.89
     Radioactive
    0.86
     Stable
    0.85
     stable
    0.85
     isoto
    0.84
    Activations Density 0.632%

    No Known Activations