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. 2-GEMMASCOPE-RES-16K
    6. 15008
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax and structure elements in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SizeF
    -0.75
    GraphicsUnit
    -0.73
    Tē
    -0.68
    fastjson
    -0.68
    usermodel
    -0.67
    olfen
    -0.63
    IsPostBack
    -0.62
     incin
    -0.62
    ibatis
    -0.61
     Enix
    -0.61
    POSITIVE LOGITS
     مشين
    0.89
    RenderAtEndOf
    0.80
    UnsafeEnabled
    0.75
    AutoresizingMask
    0.66
    														
    0.60
    Hentet
    0.59
    …………………………………………
    0.59
    																
    0.58
     autorytatywna
    0.56
    															
    0.56
    Activations Density 0.571%

    No Known Activations