© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 221
    Prev
    Next
    INDEX
    Explanations

    numeric values and mathematical references

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

    numerical values and punctuation marks in mathematical contexts

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

    references to academic papers

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     Efq
    -0.66
     HasFactory
    -0.61
     myſelf
    -0.56
    Obrázky
    -0.54
    TextEditing
    -0.53
    Tentang
    -0.52
    TextFormField
    -0.51
     Theſe
    -0.51
     دریافت‌شده
    -0.51
    ècie
    -0.50
    POSITIVE LOGITS
    rawDesc
    0.63
     online
    0.56
    #+#
    0.55
    raborty
    0.53
    addContainerGap
    0.53
     URL
    0.51
    DockStyle
    0.50
     Online
    0.50
    irov
    0.50
     Bite
    0.49
    Activations Density 0.107%

    No Known Activations