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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 105014
    Prev
    Next
    INDEX
    Explanations

    the verb "have" in various contexts related to possession or obligation

    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
     chrétien
    -0.57
     meurt
    -0.47
     vôtre
    -0.45
     nôtre
    -0.43
     recueil
    -0.42
     muere
    -0.41
     crece
    -0.41
     règne
    -0.39
     vêtement
    -0.38
     poète
    -0.37
    POSITIVE LOGITS
     have
    0.91
    have
    0.87
     had
    0.87
    MenuInflater
    0.85
    llac
    0.83
     lenker
    0.81
    ſcher
    0.80
    Have
    0.75
    iſche
    0.74
    ロウィン
    0.73
    Activations Density 0.028%

    No Known Activations