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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 16-GEMMASCOPE-RES-16K
    6. 171
    Prev
    Next
    INDEX
    Explanations

    mentions of fruits and their diversity in various contexts

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

    "fruit" or "fruits."

    np_acts-logits-general · gemini-2.0-flash

    fruit and vegetables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Burrow
    -0.56
     Petrov
    -0.54
    regs
    -0.54
    mycompany
    -0.53
    儡
    -0.53
    odule
    -0.53
     Hoffman
    -0.52
     métro
    -0.52
    sige
    -0.52
     Lins
    -0.51
    POSITIVE LOGITS
     fruits
    1.59
     fruit
    1.54
     Fruits
    1.49
    fruits
    1.42
     Fruit
    1.42
     FRUIT
    1.39
    fruit
    1.35
    Fruits
    1.35
    Fruit
    1.33
     fruity
    1.24
    Activations Density 0.192%

    No Known Activations