© 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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 80998
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "cast" in various contexts

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

    cast followed by other words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     betweenstory
    -0.60
     للمعارف
    -0.58
    IANGLES
    -0.54
     Amic
    -0.53
     Agre
    -0.53
     $_(
    -0.53
     surla
    -0.52
     marginTop
    -0.52
     Amigo
    -0.52
    Rptr
    -0.50
    POSITIVE LOGITS
     Cast
    1.09
     cast
    1.03
    cast
    1.01
    Cast
    0.95
     CAST
    0.90
    CAST
    0.82
     casting
    0.77
     casts
    0.77
     Casting
    0.75
     Kast
    0.72
    Activations Density 0.012%

    No Known Activations