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. 16325
    Prev
    Next
    INDEX
    Explanations

    references to LinkedIn and related API interactions

    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
    dafx
    -0.53
    EDEFAULT
    -0.50
    oneofs
    -0.50
    XmlAccessType
    -0.50
    parsedMessage
    -0.49
     AttributeSet
    -0.48
     NSCoder
    -0.48
    StoreMessageInfo
    -0.45
    ThroughAttribute
    -0.45
     صوتيه
    -0.44
    POSITIVE LOGITS
    ationale
    0.42
    iyaki
    0.42
    olson
    0.42
     Reſ
    0.40
     secre
    0.40
    RestClient
    0.39
     Rosario
    0.39
    <>
    
    0.38
     Contempor
    0.38
    anze
    0.38
    Activations Density 0.029%

    No Known Activations