Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 15613
    Prev
    Next
    INDEX
    Explanations

    instances of the word "had" and its context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wiſe
    -0.59
    AnimationsModule
    -0.54
     perſon
    -0.53
     ſtre
    -0.51
     itſelf
    -0.49
     ainfi
    -0.48
    ſelves
    -0.47
     ſon
    -0.47
    isTrue
    -0.46
     faſt
    -0.45
    POSITIVE LOGITS
     had
    1.15
    Had
    1.09
    had
    1.05
     Had
    1.02
     HAD
    0.90
    HAD
    0.87
     Hadley
    0.72
     Hadid
    0.69
     hatten
    0.67
     Hadrian
    0.66
    Activations Density 0.136%

    No Known Activations