© 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. 8-GEMMASCOPE-RES-16K
    11. 6202
    Prev
    Next
    INDEX
    Explanations

    the word "which" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ed
    -0.74
    ded
    -0.71
     Baton
    -0.70
    cy
    -0.68
    o
    -0.67
    СТЬ
    -0.67
     Folsom
    -0.66
     viață
    -0.65
    ことはない
    -0.64
     Hov
    -0.64
    POSITIVE LOGITS
     WHICH
    1.44
    Datuak
    1.31
     Which
    1.30
    Which
    1.22
    which
    1.21
     which
    1.19
     wich
    1.09
    ]**
    1.08
    ArgsConstructor
    0.98
    ']))
    0.96
    Activations Density 0.182%

    No Known Activations