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. 12629
    Prev
    Next
    INDEX
    Explanations

    references to health-related assessments and rights

    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
     Efq
    -0.90
     myſelf
    -0.88
     itſelf
    -0.87
     Monfieur
    -0.83
     themſelves
    -0.83
     ―――――
    -0.76
     Theſe
    -0.74
     uſe
    -0.73
     whoſe
    -0.73
     poffible
    -0.73
    POSITIVE LOGITS
    出版年
    0.70
    phant
    0.63
    rítica
    0.59
    OGND
    0.57
     stessi
    0.52
    principalTable
    0.52
     Ram
    0.50
    complexContent
    0.47
    ContentAsync
    0.47
     di
    0.47
    Activations Density 0.107%

    No Known Activations