© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 16083
    Prev
    Next
    INDEX
    Explanations

    references to specific actors and shows within the context of fan discussions

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

    Science fiction references

    np_acts-logits-general · gemini-2.0-flash

    sci-fi series titles

    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
     referenties
    -0.82
     تانيه
    -0.69
    contentLoaded
    -0.66
    
    -0.65
     Meksiku
    -0.62
    хьтан
    -0.60
    autaire
    -0.59
    TextHelper
    -0.57
     nct
    -0.56
    AutoScaleMode
    -0.55
    POSITIVE LOGITS
     Spock
    0.75
    🖖
    0.60
     Trek
    0.59
     Picard
    0.57
    Trek
    0.57
    borderSide
    0.56
    vosti
    0.54
     Scotty
    0.52
    ergic
    0.52
     USS
    0.51
    Activations Density 0.148%

    No Known Activations