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. 20-GEMMASCOPE-RES-16K
    6. 7482
    Prev
    Next
    INDEX
    Explanations

    compounds related to various types of polymers and polysaccharides

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CloseOperation
    -1.13
     متعلقه
    -1.02
     AttributeSet
    -1.00
    StoryboardSegue
    -0.99
    sizeCache
    -0.94
     AssemblyCulture
    -0.93
    WebVitals
    -0.93
    fjspx
    -0.92
    PageContext
    -0.88
     sumpay
    -0.86
    POSITIVE LOGITS
     Pol
    0.72
     POL
    0.71
     pol
    0.68
    Pol
    0.66
     Pollack
    0.65
    pol
    0.59
     pols
    0.54
     Poly
    0.49
    ポリ
    0.47
     Pola
    0.46
    Activations Density 0.126%

    No Known Activations