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. 111639
    Prev
    Next
    INDEX
    Explanations

    phrases related to perceptions of public institutions and their accountability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     CallOverrides
    -0.44
    AsUp
    -0.38
    NullCheck
    -0.34
    ByType
    -0.34
    Bottom
    -0.33
     समीक्षाओं
    -0.33
     AppCompatTheme
    -0.32
    Спасылкі
    -0.31
    tese
    -0.31
    melissa
    -0.31
    POSITIVE LOGITS
     profesión
    0.60
     profession
    0.54
    تقاوى
    0.50
     Paglinawan
    0.49
    RTDA
    0.47
     Profession
    0.47
    ngdoc
    0.47
    Chham
    0.46
     beroep
    0.45
     silicona
    0.45
    Activations Density 0.117%

    No Known Activations