© 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. 0-GEMMASCOPE-RES-16K
    11. 5895
    Prev
    Next
    INDEX
    Explanations

    terms that relate to advantages or positive outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    httphttps
    -0.71
    لينكات
    -0.57
    RAEL
    -0.53
    urato
    -0.52
    indelijk
    -0.52
    しまう
    -0.50
    ="<?=$
    -0.49
    drawText
    -0.49
     scraps
    -0.49
    はじめに
    -0.49
    POSITIVE LOGITS
    effect
    1.51
    Effect
    1.41
     Effect
    1.36
     effect
    1.36
     EFFECT
    1.32
    Benefit
    1.24
     benefit
    1.22
    benefit
    1.18
     Benefit
    1.16
     Effekt
    1.13
    Activations Density 0.234%

    No Known Activations