© 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. 887
    Prev
    Next
    INDEX
    Explanations

    variations of the syllable "ta" in different contexts

    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
    \{\\
    -0.83
     NSCoder
    -0.70
    WithIOException
    -0.69
     myſelf
    -0.66
     itſelf
    -0.65
    verwijspagina
    -0.64
    ynchronously
    -0.60
     purpoſe
    -0.60
     Eſ
    -0.59
     بيها
    -0.59
    POSITIVE LOGITS
    ta
    2.69
    TA
    1.87
     ta
    1.66
    Ta
    1.65
     Ta
    1.55
    та
    1.45
     TA
    1.34
    tas
    1.23
     Tap
    1.22
    tap
    1.22
    Activations Density 2.007%

    No Known Activations