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. 130951
    Prev
    Next
    INDEX
    Explanations

    phrases related to the evaluation of proposed methodologies and their effectiveness

    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
    WriteTagHelper
    -0.71
    WebVitals
    -0.69
    parsedMessage
    -0.68
    AddTagHelper
    -0.68
    RectangleBorder
    -0.63
    TypedDataSet
    -0.62
     виправивши
    -0.61
    tagHelperRunner
    -0.60
     intStringLen
    -0.60
    wapV
    -0.59
    POSITIVE LOGITS
     ti
    0.36
     examples
    0.36
     comments
    0.35
     example
    0.35
     true
    0.34
     saved
    0.33
     new
    0.33
     prompt
    0.33
     social
    0.32
     Example
    0.31
    Activations Density 0.131%

    No Known Activations