© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 28297
    Prev
    Next
    INDEX
    Explanations

    mathematical terminology related to ideal structures in ring theory

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

    mathematical commutative structures

    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
    ragan
    -0.56
    Viitteet
    -0.51
    styleType
    -0.47
    요
    -0.47
    XmlAccessType
    -0.47
     makam
    -0.46
     gek
    -0.45
     Hov
    -0.43
    قق
    -0.41
     parc
    -0.41
    POSITIVE LOGITS
    rrggbb
    0.73
     commutative
    0.70
    commutative
    0.67
     shopping
    0.66
     Shopping
    0.66
     Winaray
    0.66
     commut
    0.63
    Shopping
    0.59
    ftagPool
    0.59
     shops
    0.58
    Activations Density 0.320%

    No Known Activations