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 - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 131
    Prev
    Next
    INDEX
    Explanations

    references to multimedia content, particularly structured data about media releases and characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_8/width_16k/average_l0_99
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.52
    GenerationType
    -0.47
    为止
    -0.41
    XtraReports
    -0.39
    Cyfarwyddwr
    -0.39
    SharedDtor
    -0.39
     ciascuno
    -0.39
     наконец
    -0.38
    Зага
    -0.38
     scale
    -0.37
    POSITIVE LOGITS
     intptr
    0.57
     Movies
    0.47
     Numerade
    0.47
    movies
    0.41
    Movies
    0.39
     Vapour
    0.38
    movie
    0.38
     Movie
    0.38
    Movie
    0.38
     Manga
    0.36
    Activations Density 0.407%

    No Known Activations