© 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 - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 27935
    Prev
    Next
    INDEX
    Explanations

    sequences of whitespace or structured code elements within programming-related text

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

    code comments and tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    最快更新
    -0.69
     évi
    -0.68
     Strickland
    -0.65
    TableAdapter
    -0.63
    SOUNDBITE
    -0.63
     Pender
    -0.61
     nomme
    -0.61
    ophi
    -0.61
     dra
    -0.60
    Portale
    -0.60
    POSITIVE LOGITS
     الحره
    0.82
     שוליים
    0.74
    躇
    0.72
     Audiodateien
    0.69
     nakalista
    0.68
    <tr>
    0.65
    </h6>
    0.64
     فريبيس
    0.63
    GEBURTS
    0.62
    }{*}{}
    0.61
    Activations Density 0.010%

    No Known Activations