© 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. 20-GEMMASCOPE-RES-16K
    11. 13069
    Prev
    Next
    INDEX
    Explanations

    various methods, techniques, and strategies used in scientific research and analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    research methods or strategies

    np_acts-logits-general · gemini-2.0-flash

    describing methods for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aarrggbb
    -0.96
     يتيمه
    -0.93
    TagMode
    -0.89
    hoeddwyd
    -0.86
    ftagPool
    -0.85
     AssemblyCompany
    -0.77
    twimg
    -0.76
    ">//
    -0.75
    awtextra
    -0.71
     pleaſure
    -0.70
    POSITIVE LOGITS
     for
    1.31
     zur
    0.82
     used
    0.76
     для
    0.75
    用于
    0.73
     untuk
    0.70
     to
    0.69
     designed
    0.69
     برای
    0.66
    สำหรับ
    0.66
    Activations Density 0.746%

    No Known Activations