© 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-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 9989
    Prev
    Next
    INDEX
    Explanations

    references to the term "cast" and related contexts, particularly in artistic or judicial settings

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

    "cast" (or its variations)

    np_acts-logits-general · gemini-2.0-flash

    cast iron and wheels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     SwitchCompat
    -1.05
     Wikimedijinoj
    -1.03
     SDLK
    -1.01
    ViewFeatures
    -1.01
    ussis
    -1.00
     itſelf
    -0.99
    بوابة
    -0.98
     }}"></
    -0.97
    Portale
    -0.96
     photolibrary
    -0.96
    POSITIVE LOGITS
     Cast
    1.36
    Cast
    1.23
     cast
    1.21
     CAST
    1.11
    cast
    1.06
     casting
    0.99
    CAST
    0.96
     casts
    0.95
     Casting
    0.91
     Kast
    0.86
    Activations Density 0.067%

    No Known Activations