© 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. 20-GEMMASCOPE-RES-16K
    6. 8357
    Prev
    Next
    INDEX
    Explanations

    contexts related to events or activities involving participants and specifics of location or timing

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

    Appearing within quoted text or code

    np_acts-logits-general · gemini-2.0-flash

    Kashmir, Srinagar, Jammu

    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
     Waray
    -0.53
    Hosting
    -0.49
    acia
    -0.48
     rifi
    -0.47
    ₦
    -0.46
    racha
    -0.46
    ména
    -0.45
    yacht
    -0.45
    ophageal
    -0.45
    Screen
    -0.44
    POSITIVE LOGITS
     Kashmir
    1.04
     Jammu
    0.94
     Srinagar
    0.91
    Kash
    0.87
    Srin
    0.79
     Kash
    0.72
    apimachinery
    0.66
     propOrder
    0.66
     مشين
    0.64
    PhysRevD
    0.64
    Activations Density 0.031%

    No Known Activations