© 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. 15-GEMMASCOPE-RES-16K
    11. 3925
    Prev
    Next
    INDEX
    Explanations

    references to rare items or collectibles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    تقاوى
    -0.58
    SharedDtor
    -0.57
    erunner
    -0.53
    QMetaType
    -0.52
     defaultstate
    -0.51
     arşivlendi
    -0.51
    nsis
    -0.51
     surla
    -0.51
     <>",
    -0.51
    GIVEREF
    -0.49
    POSITIVE LOGITS
     random
    1.76
     randomly
    1.69
    random
    1.51
     randomness
    1.48
     Random
    1.46
     RANDOM
    1.45
    Random
    1.44
    随机
    1.32
     alé
    1.22
    RANDOM
    1.19
    Activations Density 0.629%

    No Known Activations