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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 56569
    Prev
    Next
    INDEX
    Explanations

    segments of code and their documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <eos>
    -0.74
    expandindo
    -0.66
    apimachinery
    -0.55
     pelle
    -0.43
    Enllaces
    -0.42
     Bue
    -0.41
     Arm
    -0.41
     
    -0.40
    BeginInit
    -0.40
    スピ
    -0.40
    POSITIVE LOGITS
    setVerticalGroup
    0.97
     kasarigan
    0.82
     محفوظة
    0.77
    findpost
    0.75
    脚注の使い方
    0.73
     оригіналу
    0.73
    \}\\
    0.71
    ⋱
    0.66
    ">:
    0.66
     autorytatywna
    0.66
    Activations Density 0.109%

    No Known Activations