© 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 - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 1249
    Prev
    Next
    INDEX
    Explanations

    references to tricks or strategies

    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
    PerformLayout
    -0.85
    WireFormatLite
    -0.81
    Parcelize
    -0.80
     MessageBoxIcon
    -0.79
    :✨
    -0.78
    setVerticalGroup
    -0.78
     verla
    -0.74
    \{\\
    -0.74
    Personendaten
    -0.73
     autorytatywna
    -0.72
    POSITIVE LOGITS
     advice
    1.30
     tricks
    1.23
     trick
    1.21
     Advice
    1.08
    advice
    1.05
    Advice
    1.04
     Tricks
    1.02
     ADVICE
    1.02
     tips
    1.00
    tricks
    0.97
    Activations Density 0.053%

    No Known Activations