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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 12-GEMMASCOPE-RES-16K
    6. 7674
    Prev
    Next
    INDEX
    Explanations

    references to various types of beans and bean-related products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Hozzáférés
    -1.02
    @[+][
    -0.96
    expandindo
    -0.94
    UnknownFieldSet
    -0.93
    Биография
    -0.92
    HasIndex
    -0.92
    inguém
    -0.88
    AsUp
    -0.88
     femininas
    -0.87
     оригіналу
    -0.86
    POSITIVE LOGITS
     beans
    1.53
     Beans
    1.51
     bean
    1.49
     Bean
    1.48
    Bean
    1.45
    beans
    1.35
    bean
    1.33
    Beans
    1.31
    BEAN
    0.87
     Bea
    0.86
    Activations Density 0.422%

    No Known Activations