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. 114898
    Prev
    Next
    INDEX
    Explanations

    code and functions related to database and environment variable handling

    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
     CLAIM
    -0.39
     theo
    -0.38
     claim
    -0.36
    尺
    -0.36
    ETERS
    -0.35
    laim
    -0.35
    ARROLL
    -0.34
     Byers
    -0.34
    claim
    -0.34
    lighted
    -0.34
    POSITIVE LOGITS
     незавершена
    0.65
    dotenv
    0.63
     resourceCulture
    0.58
    Diweddarwch
    0.57
    NameInMap
    0.56
    UrlResolution
    0.55
    ArgsConstructor
    0.54
     firebaseConfig
    0.53
    afficheront
    0.53
    Personensuche
    0.53
    Activations Density 0.059%

    No Known Activations