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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 10766
    Prev
    Next
    INDEX
    Explanations

    references to apples and apple-based products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     CreateTagHelper
    -0.52
    colage
    -0.49
    RegistryLite
    -0.49
    WIDE
    -0.46
    tagHelperRunner
    -0.46
    hef
    -0.45
    urman
    -0.45
    gout
    -0.45
    vantaged
    -0.45
    мум
    -0.45
    POSITIVE LOGITS
     apples
    1.03
     apple
    1.02
     manzanas
    0.95
     Apples
    0.91
    Apples
    0.89
     manzana
    0.89
     Apple
    0.83
    Apple
    0.82
     pommes
    0.81
    🍎
    0.80
    Activations Density 0.004%

    No Known Activations