© 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. 15765
    Prev
    Next
    INDEX
    Explanations

    the word "mainly" and its variants, indicating a focus on primary characteristics or functions

    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
     iVar
    -0.66
    Captor
    -0.61
     viață
    -0.58
    removeAttribute
    -0.58
    epik
    -0.58
     glycerin
    -0.57
    persky
    -0.55
    Touch
    -0.54
     chamomile
    -0.54
    orrhea
    -0.54
    POSITIVE LOGITS
     mainly
    2.44
     Mainly
    2.40
    Mostly
    2.27
     Mostly
    2.27
     mostly
    2.22
    Mainly
    2.22
    mainly
    2.20
     primarily
    2.17
     Primarily
    2.08
    mostly
    2.07
    Activations Density 0.154%

    No Known Activations