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. 2815
    Prev
    Next
    INDEX
    Explanations

    references to the term "arm" and its contextual uses related to chairs or positioning

    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
    IUrlHelper
    -0.72
    Rüyada
    -0.69
    GEBURTSDATUM
    -0.66
     متعلقه
    -0.63
    tring
    -0.63
     GetEnumerator
    -0.61
    Rè
    -0.61
     hapa
    -0.60
    SharedCtor
    -0.58
     FBref
    -0.55
    POSITIVE LOGITS
     Arm
    0.92
     arms
    0.89
     Arms
    0.88
     arm
    0.86
    Arm
    0.82
    Arms
    0.80
    chairs
    0.77
     ARM
    0.76
     lengan
    0.72
    chair
    0.72
    Activations Density 0.083%

    No Known Activations