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. 756
    Prev
    Next
    INDEX
    Explanations

    sentences expressing challenges or problems faced in various situations

    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
     skå
    -0.40
    enterOuterAlt
    -0.40
    المناصب
    -0.35
     ModelRenderer
    -0.34
     scienza
    -0.31
     Diakses
    -0.31
     AppCompat
    -0.30
     فہرست
    -0.30
     actionPerformed
    -0.30
     insight
    -0.29
    POSITIVE LOGITS
     lack
    0.59
     PROBLEM
    0.59
     shortage
    0.57
    tanleria
    0.56
     Problem
    0.55
    problem
    0.55
     mangel
    0.55
     inability
    0.54
     समस्या
    0.54
    Problem
    0.54
    Activations Density 0.047%

    No Known Activations