© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 12888
    Prev
    Next
    INDEX
    Explanations

    programming language constructs and data types in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     forfait
    -0.61
    发表于
    -0.58
     pleaſure
    -0.55
    ública
    -0.54
     preſent
    -0.54
    hésite
    -0.53
     opportunities
    -0.52
    %)$
    -0.52
    öglichkeiten
    -0.51
     Hift
    -0.50
    POSITIVE LOGITS
    Hochspringen
    0.60
    原始内容存档于
    0.57
     bes
    0.57
    numerusform
    0.55
     Cos
    0.54
    ANTLR
    0.52
    gbaar
    0.51
    scriptcase
    0.51
    ajte
    0.51
    ptonshire
    0.50
    Activations Density 2.233%

    No Known Activations