© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14619
    Prev
    Next
    INDEX
    Explanations

    events or announcements followed by recent activity

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

    preceding verbs indicating an action or announcement

    np_acts-logits-general · gemini-2.0-flash

    just announced or started

    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
     existed
    -0.67
     exist
    -0.63
     dwells
    -0.62
    kept
    -0.62
     Exist
    -0.61
     existence
    -0.61
     exists
    -0.61
     iniziale
    -0.59
     {};
    -0.57
     ajan
    -0.57
    POSITIVE LOGITS
     announce
    1.01
     announced
    0.99
     launch
    0.89
     officially
    0.88
     announces
    0.86
     launched
    0.82
     announcing
    0.81
     completed
    0.79
     successfully
    0.76
     unveiled
    0.75
    Activations Density 0.473%

    No Known Activations