© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 5443
    Prev
    Next
    INDEX
    Explanations

    URLs and web links in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FFFFFFFF
    -0.49
    GraphicsUnit
    -0.46
    锈钢
    -0.43
    värr
    -0.42
    widetext
    -0.42
    ViewById
    -0.41
    onsored
    -0.41
    MergeFrom
    -0.40
    ModelBuilder
    -0.40
     +%
    -0.37
    POSITIVE LOGITS
     tabPage
    0.73
    出版年
    0.73
    MENAFN
    0.71
    oa̍t
    0.66
    jstor
    0.63
     ThemeData
    0.62
    مصادر
    0.60
    httphttps
    0.60
    以上就是
    0.57
     solitaire
    0.57
    Activations Density 0.021%

    No Known Activations