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. 12497
    Prev
    Next
    INDEX
    Explanations

    structured descriptions of neural network architectures

    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
    ApiModel
    -0.54
     Trọng
    -0.52
     HttpHeaders
    -0.49
    вгения
    -0.48
     caught
    -0.46
    hynch
    -0.46
    Hypo
    -0.45
    arroz
    -0.45
     Webster
    -0.45
     Stroh
    -0.45
    POSITIVE LOGITS
    nestjs
    0.70
    OGND
    0.69
    Jeografia
    0.67
    المناصب
    0.67
     NgModule
    0.66
    queryInterface
    0.65
    AddTagHelper
    0.64
     שוליים
    0.61
    MemoryWarning
    0.61
     StatelessWidget
    0.61
    Activations Density 0.058%

    No Known Activations