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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 3463
    Prev
    Next
    INDEX
    Explanations

    references to TV shows, particularly focusing on their titles and current seasons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Initializable
    -0.51
    hyrchwyd
    -0.49
    uckle
    -0.49
    zeti
    -0.46
     autem
    -0.46
    idem
    -0.46
     surla
    -0.45
    ეტ
    -0.45
    GetItem
    -0.44
     trang
    -0.44
    POSITIVE LOGITS
    تقاوى
    0.79
    /******/
    0.57
    /***/
    0.56
    CloseOperation
    0.55
    ScopeManager
    0.53
    PropertyChanging
    0.52
     насељу
    0.50
    aarrggbb
    0.49
     légales
    0.48
     pinulongan
    0.48
    Activations Density 0.254%

    No Known Activations