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. 111582
    Prev
    Next
    INDEX
    Explanations

    quantitative data related to expenditures, production, and viewership statistics

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

    slaves owned, suffering from

    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
    
    -0.54
    sidemargin
    -0.52
    principalColumn
    -0.52
     يتيمه
    -0.49
    featureID
    -0.47
     BoxFit
    -0.45
     Мексичка
    -0.45
     resourceCulture
    -0.45
    tonode
    -0.45
    +#+#
    -0.44
    POSITIVE LOGITS
    hoeddwyd
    0.42
     ciudadana
    0.41
     officially
    0.41
     registered
    0.40
     estimated
    0.39
    Referanser
    0.39
    alue
    0.38
     recorded
    0.38
    Eksterne
    0.38
     collectively
    0.38
    Activations Density 0.030%

    No Known Activations