Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 38997
    Prev
    Next
    INDEX
    Explanations

    terms related to user authentication and security in programming contexts

    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
     defaultstate
    -0.79
    ReusableCell
    -0.78
    MLLoader
    -0.56
     الرياضيه
    -0.54
    AutoField
    -0.53
    findpost
    -0.52
     utafitiHapana
    -0.51
    MemoryWarning
    -0.50
    delwed
    -0.50
    يكب
    -0.50
    POSITIVE LOGITS
    Security
    0.68
     security
    0.67
     Security
    0.65
    SECURITY
    0.63
    security
    0.60
     SECURITY
    0.58
     sécurité
    0.53
    curité
    0.44
    SupportActionBar
    0.44
     seguridad
    0.43
    Activations Density 0.003%

    No Known Activations