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. 117402
    Prev
    Next
    INDEX
    Explanations

    important notions regarding community health and welfare

    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
     smiles
    -0.28
     raised
    -0.28
    érias
    -0.28
    い
    -0.28
     Raised
    -0.28
     chuckles
    -0.26
    tine
    -0.26
    Rüyada
    -0.26
    Raised
    -0.26
    ↵
    -0.25
    POSITIVE LOGITS
    ########.
    0.82
    GEBURTSDATUM
    0.70
     Administrativna
    0.70
    цездатний
    0.69
    tvguidetime
    0.68
     otomatig
    0.68
    EDEFAULT
    0.67
    numerusform
    0.67
    balleur
    0.67
    <unused43>
    0.64
    Activations Density 0.043%

    No Known Activations