© 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-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 10470
    Prev
    Next
    INDEX
    Explanations

    the word "Cast" and its variations, indicating a focus on references to film or theatrical casts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mexique
    -0.41
     Dulce
    -0.39
     abuso
    -0.39
     régle
    -0.39
     mực
    -0.36
     bénévol
    -0.36
     voluntarios
    -0.35
    rası
    -0.35
     Conseils
    -0.35
     emoción
    -0.35
    POSITIVE LOGITS
     Cast
    1.26
     cast
    1.23
     CAST
    1.12
    Cast
    1.09
     casts
    1.06
     casting
    1.02
    cast
    0.94
     Casting
    0.94
    CAST
    0.88
    casts
    0.85
    Activations Density 0.079%

    No Known Activations