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. 7401
    Prev
    Next
    INDEX
    Explanations

    references to user experiences and interactions with products or services

    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
     plupart
    -0.85
     maioria
    -0.84
     anyone
    -0.83
     każdej
    -0.83
     fleste
    -0.83
     każdy
    -0.83
    どれも
    -0.82
     flesta
    -0.82
    anyone
    -0.81
     anybody
    -0.81
    POSITIVE LOGITS
     addirittura
    0.92
     outright
    0.88
     may
    0.88
     chiar
    0.82
     downright
    0.82
    甚至是
    0.81
     sogar
    0.79
     even
    0.78
     simply
    0.77
     might
    0.75
    Activations Density 0.553%

    No Known Activations