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
    4. Residual Stream - 131k
    5. 23-GEMMASCOPE-RES-131K
    6. 118
    Prev
    Next
    INDEX
    Explanations

    prepositions and possessive forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_131k/average_l0_101
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gjenge
    -0.50
     Komunikasi
    -0.41
    https
    -0.41
     húmedo
    -0.41
     chrétien
    -0.40
     årene
    -0.40
     extranjero
    -0.40
     vœ
    -0.40
     âgé
    -0.39
     lendemain
    -0.38
    POSITIVE LOGITS
     utafitiHapana
    0.96
     của
    0.82
    ของ
    0.80
    オブ
    0.75
    Clik
    0.73
     OF
    0.71
     of
    0.71
     dieſer
    0.69
     للمعارف
    0.69
    ArgsConstructor
    0.68
    Activations Density 0.000%

    No Known Activations