© 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. 4-GEMMASCOPE-RES-16K
    11. 11311
    Prev
    Next
    INDEX
    Explanations

    relative pronouns and interrogative words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Baton
    -0.70
    ed
    -0.67
     relationship
    -0.63
     Dampf
    -0.63
     Tief
    -0.62
    Aly
    -0.61
     Folsom
    -0.61
    Peek
    -0.60
    rüstung
    -0.59
    tony
    -0.59
    POSITIVE LOGITS
     WHICH
    1.85
     which
    1.77
    which
    1.71
     Which
    1.64
    Which
    1.58
     wich
    1.41
    Datuak
    1.32
    hich
    1.25
    ซึ่ง
    1.09
     welches
    1.04
    Activations Density 0.232%

    No Known Activations