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. 24-GEMMASCOPE-RES-131K
    6. 964
    Prev
    Next
    INDEX
    Explanations

    references to legal cases and associated activities

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

    prepositions followed by nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     angesch
    -0.39
    archiviato
    -0.35
     asimismo
    -0.35
     sekal
    -0.34
     Entste
    -0.34
     karşılaş
    -0.33
    f
    -0.32
     Eindruck
    -0.32
     Entstehung
    -0.32
     strijd
    -0.32
    POSITIVE LOGITS
    principalColumn
    0.81
     disambiguazione
    0.79
     Савезне
    0.76
     يتيمه
    0.71
    AddTagHelper
    0.69
     fashiola
    0.68
     ſind
    0.68
    UrlResolution
    0.68
    verwijspagina
    0.66
     Majefty
    0.65
    Activations Density 0.137%

    No Known Activations