Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 39-GEMMASCOPE-RES-16K
    6. 912
    Prev
    Next
    INDEX
    Explanations

    statistics and performance metrics related to sports players

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.96
    parsedMessage
    -0.73
    InjectAttribute
    -0.64
    SharedCtor
    -0.63
     NSCoder
    -0.60
     Theſe
    -0.60
     CreateTagHelper
    -0.58
     createState
    -0.58
     informée
    -0.58
     invokingState
    -0.56
    POSITIVE LOGITS
     en
    0.61
     while
    0.42
     overall
    0.42
     despite
    0.41
     spread
    0.36
    ながら
    0.35
     against
    0.35
     compared
    0.35
     marcado
    0.34
     behind
    0.33
    Activations Density 0.245%

    No Known Activations