© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 532
    Prev
    Next
    INDEX
    Explanations

    the start of a new section or paragraph within text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Vege
    -0.73
    +:+
    -0.72
    出版年
    -0.72
    DispatchToProps
    -0.72
    település
    -0.69
     HOY
    -0.65
    enderror
    -0.64
    MENAFN
    -0.62
    Rüyada
    -0.62
    ruptedException
    -0.62
    POSITIVE LOGITS
    <bos>
    0.90
    ↵↵
    0.61
    "
    0.59
     consultato
    0.55
    <blockquote>
    0.55
     Перейти
    0.55
    webElementXpaths
    0.54
    ↵↵↵
    0.54
    <h2>
    0.53
    [toxicity=0]
    0.53
    Activations Density 0.016%

    No Known Activations