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. 9-GEMMASCOPE-RES-16K
    6. 15103
    Prev
    Next
    INDEX
    Explanations

    C programming language syntax elements such as type definitions and function declarations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Uptake
    -0.52
    ecap
    -0.50
     esclu
    -0.49
     bottling
    -0.49
     chacune
    -0.49
     acquist
    -0.49
     tė
    -0.49
     secundario
    -0.48
    rxjs
    -0.48
     secundarios
    -0.48
    POSITIVE LOGITS
     betweenstory
    0.70
     للمعارف
    0.70
    VersionUID
    0.67
    oa̍t
    0.67
    WriteBarrier
    0.65
     AssemblyTitle
    0.62
    verwijspagina
    0.61
     المعيارى
    0.61
     nahilalakip
    0.59
     Chwiliwch
    0.58
    Activations Density 0.248%

    No Known Activations