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. 23-GEMMASCOPE-RES-131K
    6. 23129
    Prev
    Next
    INDEX
    Explanations

    numerical data or statistics in text

    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_23/width_131k/average_l0_101
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    afficheront
    -0.63
     Monfieur
    -0.59
    లాలు
    -0.59
    nsito
    -0.57
     otomatig
    -0.57
     enfans
    -0.54
     Administrativna
    -0.52
    RTLR
    -0.52
     CanadaChoose
    -0.51
    下载附件
    -0.50
    POSITIVE LOGITS
    omitempty
    0.41
    ../../../
    0.39
    Unless
    0.39
    Flan
    0.38
    одо
    0.38
    \|_{
    0.37
    óz
    0.37
     International
    0.36
    ../../
    0.36
    "@
    0.36
    Activations Density 0.023%

    No Known Activations