© 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. 9120
    Prev
    Next
    INDEX
    Explanations

    specific keywords or phrases indicating events or occurrences with some level of urgency or significance

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

    Time periods or dates

    np_acts-logits-general · gemini-2.0-flash

    upcoming periods

    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
     yesterday
    -0.93
    Yesterday
    -0.80
     last
    -0.80
     esternos
    -0.78
     вчера
    -0.78
     Yesterday
    -0.78
     recent
    -0.78
     ayer
    -0.77
    yesterday
    -0.74
     gestern
    -0.73
    POSITIVE LOGITS
    hopefully
    1.12
     hopefully
    1.06
     mendatang
    0.99
    Hopefully
    0.92
     Hopefully
    0.91
     unless
    0.88
     prochain
    0.85
     barring
    0.83
     المقبل
    0.83
    unless
    0.83
    Activations Density 0.131%

    No Known Activations