© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1371
    Prev
    Next
    INDEX
    Explanations

    references to specific weeks and their associated events or activities

    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
    いる
    -0.61
    ibatis
    -0.59
     pinulongan
    -0.52
    struzione
    -0.51
    NameInMap
    -0.51
     Lehre
    -0.50
    filesize
    -0.49
    ︎
    -0.49
    isbury
    -0.48
    hintText
    -0.46
    POSITIVE LOGITS
    ends
    1.02
    weeks
    0.95
     weeks
    0.90
     Weeks
    0.90
    night
    0.82
    Weeks
    0.81
    ender
    0.80
     WEEKS
    0.79
    ended
    0.76
     ago
    0.76
    Activations Density 0.086%

    No Known Activations