© 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-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 2716
    Prev
    Next
    INDEX
    Explanations

    references to animation and children's entertainment

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

    references to books, media, and entertainment (especially children's books and media production).

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    references to children’s/animated media and entertainment titles, including studios, cartoons, picture books, and related proper names.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    references to children's books, picture books, cartoons, and animated media.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
    SequentialGroup
    -0.70
     الحره
    -0.65
     FontWeight
    -0.58
    ConstraintMaker
    -0.55
    AnchorStyles
    -0.54
    Personensuche
    -0.54
     BorderSide
    -0.54
    ########.
    -0.53
    principalColumn
    -0.53
     Cæsar
    -0.52
    POSITIVE LOGITS
     cartoon
    0.72
     animated
    0.68
     Disney
    0.64
     cartoons
    0.62
     мульт
    0.60
     Cartoon
    0.58
     anim
    0.56
     children
    0.56
     betweenstory
    0.55
     animation
    0.53
    Activations Density 0.125%

    No Known Activations