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. 33-GEMMASCOPE-RES-131K
    6. 65838
    Prev
    Next
    INDEX
    Explanations

    special mathematical symbols and notation used in equations and formulas

    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_33/width_131k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     snippetHide
    -0.93
     ModelExpression
    -0.86
     kasarigan
    -0.80
     queſta
    -0.78
    Datuak
    -0.77
     stockbild
    -0.77
     pleaſure
    -0.77
    PerformLayout
    -0.76
    <unused41>
    -0.76
    <unused8>
    -0.76
    POSITIVE LOGITS
    )
    0.33
     +
    0.32
     plus
    0.32
    indépendance
    0.31
     otherwise
    0.31
     плюс
    0.28
     /
    0.28
     кроме
    0.28
    否则
    0.27
    ,
    0.27
    Activations Density 0.307%

    No Known Activations