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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 4622
    Prev
    Next
    INDEX
    Explanations

    code-related elements and structures within a programming context

    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
     /\.(
    -0.59
    
    -0.56
     %@",
    -0.53
     ring
    -0.47
    LookAnd
    -0.46
    pattern
    -0.45
     pattern
    -0.43
    zeu
    -0.43
     {}),
    -0.43
    deelte
    -0.43
    POSITIVE LOGITS
    :✨
    1.00
    دانشنامهٔ
    0.85
    脚注の使い方
    0.75
     arşivlendi
    0.70
    featureID
    0.70
     оригіналу
    0.69
     rowspan
    0.69
    Билгалдахарш
    0.69
    InstanceState
    0.68
    ANCE
    0.66
    Activations Density 2.039%

    No Known Activations