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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3490
    Prev
    Next
    INDEX
    Explanations

    numerical values and mathematical expressions within the text

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

    Roman numerals and numbers followed by a parenthesis

    np_acts-logits-general · gemini-2.0-flash

    list item markers followed by parenthesis

    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
    SourceChecksum
    -0.73
    MemoryWarning
    -0.70
    Pyx
    -0.62
    jspx
    -0.62
     LUMP
    -0.59
     محفوظة
    -0.59
    IBar
    -0.58
    RTLR
    -0.58
     VizieR
    -0.57
     Constitucional
    -0.57
    POSITIVE LOGITS
    )
    1.07
    )-
    0.88
    ）
    0.80
     )
    0.79
    ),
    0.79
    )"
    0.73
    )$
    0.71
    )+
    0.70
    -)
    0.70
    )
    0.70
    Activations Density 0.320%

    No Known Activations