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. 75459
    Prev
    Next
    INDEX
    Explanations

    mentions of articles, writing, and journalism-related content

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

    writing in publications

    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
     circun
    -0.35
     MonoBehaviour
    -0.34
    bcryptjs
    -0.34
    FirstResponder
    -0.33
     wireType
    -0.33
     للمعارف
    -0.33
     inmig
    -0.32
    WaitGroup
    -0.32
     pamamagitan
    -0.32
    AntiForgeryToken
    -0.32
    POSITIVE LOGITS
    ReusableCell
    0.62
    IsMutable
    0.60
     otomatig
    0.56
    noted
    0.51
     tartalomajánló
    0.48
    Démographie
    0.48
    HasAnnotation
    0.48
     castor
    0.47
    GetEnumerator
    0.47
     consultato
    0.47
    Activations Density 0.031%

    No Known Activations