© 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. 5171
    Prev
    Next
    INDEX
    Explanations

    the occurrence of the term "ta" in various contexts

    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
    addGap
    -0.57
    之
    -0.54
    zation
    -0.52
    ühen
    -0.52
    coroutines
    -0.50
    ồng
    -0.49
    ënten
    -0.49
    стран
    -0.48
     betweenstory
    -0.48
     verv
    -0.47
    POSITIVE LOGITS
    ta
    3.59
    TA
    2.60
     ta
    2.39
    Ta
    2.39
     Ta
    2.29
     TA
    2.10
    та
    1.64
    タ
    1.45
     taping
    1.44
     tap
    1.44
    Activations Density 0.070%

    No Known Activations