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. 65012
    Prev
    Next
    INDEX
    Explanations

    names of streets and locations

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

    Main Street / St

    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
     Polda
    -0.50
     Lazio
    -0.48
     '\\;'
    -0.48
     Turquía
    -0.47
    bParam
    -0.47
     Begründung
    -0.46
     Monteiro
    -0.45
     floating
    -0.45
     tropical
    -0.44
     Bangkok
    -0.44
    POSITIVE LOGITS
     "..\..\
    0.48
     BoxFit
    0.45
     "..\..\..\
    0.44
    ViewImports
    0.42
    ContentAsync
    0.40
     whiteColor
    0.39
    ınt
    0.39
    ioutil
    0.38
     الحره
    0.38
     noyau
    0.37
    Activations Density 0.008%

    No Known Activations