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. 0-GEMMASCOPE-RES-16K
    6. 9762
    Prev
    Next
    INDEX
    Explanations

    actions or verbs that indicate an ongoing process or transition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kaarangay
    -1.20
     pinulongan
    -1.04
    出版年
    -0.95
    __(/*!
    -0.92
     تضيفلها
    -0.89
    httphttps
    -0.87
    󠁿
    -0.85
    ScopeManager
    -0.82
    drawSprites
    -0.79
    +#+#
    -0.77
    POSITIVE LOGITS
    Ủ
    0.49
     onStop
    0.46
    melidir
    0.42
    شع
    0.41
    itzar
    0.40
    0.39
    วัส
    0.39
    Reparto
    0.38
     bag
    0.37
    払い
    0.37
    Activations Density 0.588%

    No Known Activations