© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 1643
    Prev
    Next
    INDEX
    Explanations

    references to companies and investments in various industries

    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
     malheureusement
    -0.74
     maravilh
    -0.71
     maravilhoso
    -0.65
    THANK
    -0.64
     wspania
    -0.64
     wonderful
    -0.63
     uncontrol
    -0.60
    Уважа
    -0.60
     unforgettable
    -0.60
    ousands
    -0.60
    POSITIVE LOGITS
     reportedly
    0.74
     undisclosed
    0.71
     expects
    0.68
    该公司
    0.68
     launched
    0.66
     unspecified
    0.65
     launch
    0.64
     its
    0.64
     deal
    0.62
     leveraging
    0.62
    Activations Density 0.238%

    No Known Activations