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
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 122906
    Prev
    Next
    INDEX
    Explanations

    the presence of assembly attributes in programming documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
     ISNI
    -0.75
    StoreMessageInfo
    -0.57
     ويكيپيديا
    -0.56
    Попис
    -0.49
     GeoNames
    -0.47
    InputTagHelper
    -0.37
    InitVars
    -0.36
     Affiliations
    -0.35
     strany
    -0.33
    JspWriter
    -0.33
    POSITIVE LOGITS
     AssemblyCulture
    3.83
     betweenstory
    2.53
    webElementXpaths
    2.47
    StructEnd
    2.06
    writeFieldEnd
    1.93
     Emits
    1.17
    sendLogPayload
    1.06
    stylers
    1.00
    tagHelperRunner
    0.98
    BoxShadow
    0.90
    Activations Density 0.000%

    No Known Activations