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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 8605
    Prev
    Next
    INDEX
    Explanations

    financial metrics and data related to annual reports and fiscal performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AsUp
    -0.54
     Besøkt
    -0.53
     tomorrow
    -0.53
    MENAFN
    -0.52
     يتيمه
    -0.52
    رشف
    -0.50
    jsonwebtoken
    -0.49
     intptr
    -0.49
     λί
    -0.48
     насељу
    -0.48
    POSITIVE LOGITS
    ViewFeatures
    0.86
     fiscal
    0.70
     onData
    0.64
    fiscal
    0.63
     audited
    0.61
     Fiscal
    0.58
     ragaz
    0.57
     census
    0.56
     AspNetCore
    0.54
    dited
    0.54
    Activations Density 0.206%

    No Known Activations