© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 20-GEMMASCOPE-RES-16K
    11. 14776
    Prev
    Next
    INDEX
    Explanations

    references to popular TV shows and their portrayal of LGBTQ+ themes and families

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

    TV seasons or episodes

    np_acts-logits-general · gemini-2.0-flash

    TV seasons and series

    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
    UnusedPrivate
    -0.73
    SequentialGroup
    -0.71
     CreateTagHelper
    -0.64
    ništvo
    -0.59
    webElementXpaths
    -0.55
    lwjgl
    -0.55
    LookAnd
    -0.53
    esModule
    -0.50
    hObject
    -0.50
    DeleteBehavior
    -0.48
    POSITIVE LOGITS
     Season
    1.52
     season
    1.49
    Season
    1.36
    season
    1.30
     seasons
    1.27
     SEASON
    1.19
     episodes
    1.13
     series
    1.12
    SEASON
    1.07
     episode
    1.06
    Activations Density 0.361%

    No Known Activations