Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 9839
    Prev
    Next
    INDEX
    Explanations

    keywords related to media consumption and parental control over children’s exposure to content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    
    -0.77
    WithIOException
    -0.67
     mikrofon
    -0.66
    FunctionFlags
    -0.61
    LLocation
    -0.61
     pageContext
    -0.60
     saiba
    -0.60
     samarbeid
    -0.58
     partenariat
    -0.58
     defaultstate
    -0.58
    POSITIVE LOGITS
     movies
    2.04
     movie
    1.74
     films
    1.58
     Movies
    1.47
    movies
    1.45
     TV
    1.43
     television
    1.35
    movie
    1.35
    Movies
    1.33
     film
    1.32
    Activations Density 0.378%

    No Known Activations