© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 8468
    Prev
    Next
    INDEX
    Explanations

    occurrences of function-like structures and their parameters in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.68
     AssemblyCompany
    -0.61
     snippetHide
    -0.60
    sidemargin
    -0.59
     سكانية
    -0.57
    เอง
    -0.56
    
    -0.55
     desmotivaciones
    -0.55
     Gemü
    -0.55
    ьаж
    -0.54
    POSITIVE LOGITS
     f
    1.53
     F
    1.51
    f
    1.38
    F
    1.36
     getF
    1.07
    getF
    1.06
    F
    0.91
    f
    0.90
    xf
    0.88
     Ф
    0.81
    Activations Density 0.538%

    No Known Activations