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. 117336
    Prev
    Next
    INDEX
    Explanations

    numerical data, specifically financial figures and performance metrics

    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
     pinulongan
    -0.87
    Diwedd
    -0.83
     informée
    -0.79
     queſto
    -0.69
    LookAnd
    -0.69
     yyr
    -0.68
    ſelben
    -0.66
    contentLoaded
    -0.65
    <unused79>
    -0.65
    <unused68>
    -0.65
    POSITIVE LOGITS
     expected
    0.26
     съдържа
    0.26
     need
    0.26
    ự
    0.26
     whatever
    0.26
     also
    0.25
     있어
    0.25
    */}
    0.25
     as
    0.25
     answer
    0.24
    Activations Density 0.017%

    No Known Activations