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-2-2B
    4. Residual Stream - 16k
    5. 13-GEMMASCOPE-RES-16K
    6. 12824
    Prev
    Next
    INDEX
    Explanations

    references to third-party entities and their interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.76
    tagext
    -0.71
    IsContent
    -0.65
    +#+#
    -0.64
    RetentionPolicy
    -0.63
    usermodel
    -0.63
     estekak
    -0.62
    Попис
    -0.62
    ьаж
    -0.61
    usercontent
    -0.60
    POSITIVE LOGITS
     outside
    0.85
    outside
    0.75
     external
    0.71
     guest
    0.69
     Guest
    0.68
     Outside
    0.67
     terceros
    0.67
     خارجی
    0.64
     terceiros
    0.64
     externes
    0.64
    Activations Density 0.470%

    No Known Activations