© 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. 4-GEMMASCOPE-RES-16K
    11. 12647
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate relationships or references to objects and their locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    latego
    -0.64
    tencent
    -0.59
    givings
    -0.54
    YMMV
    -0.53
    continence
    -0.53
    tubers
    -0.52
    nál
    -0.52
    rohr
    -0.51
     Zanzibar
    -0.51
     xpath
    -0.51
    POSITIVE LOGITS
     ویکی‌پدیای
    0.66
    onAttach
    0.66
    تقاوى
    0.63
    كويكب
    0.61
     defaultstate
    0.58
     Chwiliwch
    0.58
    GOTREF
    0.56
     esternos
    0.55
    примеча
    0.55
     Ewig
    0.55
    Activations Density 0.320%

    No Known Activations