© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 5816
    Prev
    Next
    INDEX
    Explanations

    words related to tricks or deceptive practices

    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
    Бахар
    -0.74
    tldr
    -0.64
    PerformLayout
    -0.60
    ="#"><
    -0.59
    Naissance
    -0.57
    发表于
    -0.56
     financieras
    -0.56
     váll
    -0.55
     financieros
    -0.55
    Controllo
    -0.53
    POSITIVE LOGITS
     trick
    4.82
    trick
    3.99
     Trick
    3.86
     tricks
    3.59
    Trick
    3.49
     Tricks
    2.99
    tricks
    2.98
     truco
    2.65
     tricked
    2.15
     trucos
    1.96
    Activations Density 0.081%

    No Known Activations