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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 21-GEMMASCOPE-RES-16K
    6. 12523
    Prev
    Next
    INDEX
    Explanations

    specialized syntax and structure in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     couvert
    -0.44
    ที่สุด
    -0.43
     Included
    -0.42
     utara
    -0.42
     cubierto
    -0.42
    Included
    -0.40
     innova
    -0.39
    includes
    -0.38
    الد
    -0.38
    included
    -0.38
    POSITIVE LOGITS
    InjectAttribute
    1.05
    WriteBarrier
    0.94
     ModelExpression
    0.94
    Personendaten
    0.94
    abestanden
    0.88
    sizeCache
    0.84
    MLLoader
    0.84
     protoimpl
    0.82
    protoimpl
    0.81
    rungsseite
    0.79
    Activations Density 0.272%

    No Known Activations