© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 5956
    Prev
    Next
    INDEX
    Explanations

    instances of the word "extensive" indicating detailed descriptions or thoroughness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Clik
    -0.67
    ReusableCell
    -0.63
    t
    -0.59
     saith
    -0.55
    竺
    -0.53
     Bebe
    -0.53
    Datuak
    -0.53
     Diener
    -0.52
     Nem
    -0.52
    ে
    -0.51
    POSITIVE LOGITS
     extensive
    2.71
     Extensive
    2.61
    Extensive
    2.61
    extensive
    2.59
     extensively
    1.98
     umfang
    1.69
     exhaustive
    1.59
     intensive
    1.55
     comprehensive
    1.53
     extensa
    1.53
    Activations Density 0.081%

    No Known Activations