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. 38861
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate lack of warranties or conditions

    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
    SharedCtor
    -0.57
    parsedMessage
    -0.56
    tagext
    -0.51
    HomeAsUpEnabled
    -0.51
    PYX
    -0.50
    orianCalendar
    -0.47
     GenerationType
    -0.45
    usermodel
    -0.41
    ExtendWith
    -0.41
     HttpNotFound
    -0.41
    POSITIVE LOGITS
    Portale
    0.56
    StylePriority
    0.44
     nakalista
    0.44
    Portail
    0.39
    AddTagHelper
    0.38
     LIRE
    0.38
     própri
    0.37
    ValueStyle
    0.37
     WARRANTIES
    0.37
     HttpServlet
    0.37
    Activations Density 0.003%

    No Known Activations