© 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. 25-GEMMASCOPE-RES-16K
    11. 4101
    Prev
    Next
    INDEX
    Explanations

    promotional offers related to products, specifically focusing on shipping and discounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awtextra
    -0.52
    AndEndTag
    -0.51
    anadium
    -0.49
     rospy
    -0.48
     pneumo
    -0.47
    umbus
    -0.47
    sendRedirect
    -0.46
     Chess
    -0.45
    carbu
    -0.45
    nitzel
    -0.45
    POSITIVE LOGITS
     skincare
    1.66
     Skincare
    1.52
     beauty
    1.52
     skin
    1.51
     Beauty
    1.51
     Skin
    1.47
    Skin
    1.46
    Beauty
    1.44
     cosmetics
    1.38
    beauty
    1.37
    Activations Density 0.255%

    No Known Activations