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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15745
    Prev
    Next
    INDEX
    Explanations

    phrases related to societal issues and critiques of power dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows words indicating something is small, unimportant, or "just" something

    np_acts-logits-general · gemini-2.0-flash

    not merely

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/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.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    =$?
    -0.53
    ftagPool
    -0.51
    jspx
    -0.50
    setVerticalGroup
    -0.50
     resourceCulture
    -0.49
    TagMode
    -0.49
     arşivlendi
    -0.48
     cláss
    -0.48
     segredo
    -0.48
    جیب
    -0.47
    POSITIVE LOGITS
     mere
    1.23
     merely
    1.18
    mere
    1.08
     glorified
    0.97
     مجرد
    0.86
    ただの
    0.81
     decoration
    0.79
    Mere
    0.79
     meras
    0.79
     meaningless
    0.78
    Activations Density 0.448%

    No Known Activations