© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 2161
    Prev
    Next
    INDEX
    Explanations

    references to local news broadcasts and television programming

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

    frequency or regularity

    np_acts-logits-general · gemini-2.0-flash

    currently

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     will
    -0.87
     akan
    -0.79
    will
    -0.79
     prochains
    -0.76
    Will
    -0.73
     budú
    -0.69
     sẽ
    -0.67
     lesz
    -0.67
     gonna
    -0.66
     Will
    -0.66
    POSITIVE LOGITS
     routinely
    1.04
     regularly
    1.03
     annually
    0.90
     currently
    0.82
     occasionally
    0.82
     operates
    0.80
     frequently
    0.79
     constantly
    0.77
     Regularly
    0.75
    currently
    0.75
    Activations Density 0.751%

    No Known Activations