© 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. 1-GEMMASCOPE-RES-16K
    11. 7281
    Prev
    Next
    INDEX
    Explanations

    the word "had" in various contexts, indicating a focus on past experiences or completed actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    woordig
    -0.79
    hlon
    -0.65
     knex
    -0.61
    ಿದೆ
    -0.61
    ocate
    -0.60
     perſon
    -0.60
     Olsson
    -0.60
    blume
    -0.60
    いません
    -0.59
    blumen
    -0.58
    POSITIVE LOGITS
     had
    3.57
    Had
    3.03
    had
    2.93
     Had
    2.91
     HAD
    2.66
    HAD
    2.11
     hadden
    2.06
     hadde
    1.94
     hatte
    1.93
     hatten
    1.93
    Activations Density 0.091%

    No Known Activations