Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 7021
    Prev
    Next
    INDEX
    Explanations

    elements related to violence or physical harm

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     незавершена
    -0.74
     العنوان
    -0.67
     lenker
    -0.64
    دانشنامهٔ
    -0.55
     varandra
    -0.54
    TintMode
    -0.54
     الرياضيه
    -0.52
     myö
    -0.52
     olev
    -0.52
    脚注の使い方
    -0.52
    POSITIVE LOGITS
     eyes
    1.78
     feet
    1.72
     hands
    1.62
     legs
    1.54
     ears
    1.51
     fingers
    1.49
     lips
    1.38
     arms
    1.35
     mouth
    1.33
     head
    1.32
    Activations Density 0.644%

    No Known Activations