© 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 - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 1804
    Prev
    Next
    INDEX
    Explanations

    variations of "hip" and "Hi" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mbggenerated
    -0.57
    UserScript
    -0.54
    सन्दर्भ
    -0.54
    localObject
    -0.53
    setViewportView
    -0.52
     Gabel
    -0.51
     שוליים
    -0.48
    bindParam
    -0.48
    ending
    -0.48
    IContainer
    -0.47
    POSITIVE LOGITS
     Hipp
    0.71
    Hip
    0.66
    Хи
    0.64
     Hiram
    0.63
     Hiber
    0.62
     Hip
    0.60
     hypoch
    0.59
     hips
    0.59
     Hib
    0.59
     hik
    0.58
    Activations Density 0.101%

    No Known Activations