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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 5933
    Prev
    Next
    INDEX
    Explanations

    instances of voting and selecting in various contexts

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

    actions followed by punctuation or prepositions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     يتيمه
    -0.65
     Савезне
    -0.62
     estekak
    -0.61
     Taktlose
    -0.55
    adpleegd
    -0.52
    urlpatterns
    -0.52
    fjspx
    -0.50
    PyExc
    -0.48
     ExecuteAsync
    -0.48
    RSpec
    -0.48
    POSITIVE LOGITS
    TM
    0.33
    MOL
    0.32
    executed
    0.32
    Viewer
    0.31
    ReusableCell
    0.31
     Temporary
    0.30
    TMP
    0.30
    UIControlState
    0.29
     hereby
    0.29
    Root
    0.28
    Activations Density 0.022%

    No Known Activations