© 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-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 10630
    Prev
    Next
    INDEX
    Explanations

    the form and usage of the verb "to be" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows the word "being" or "be"

    np_acts-logits-general · gemini-2.0-flash

    being + past participle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nemlig
    -0.32
    ırlı
    -0.31
     rêver
    -0.31
     ouv
    -0.31
    íná
    -0.30
     चाह
    -0.30
    removing
    -0.29
     télécharge
    -0.28
    ± 
    -0.28
     ressemb
    -0.28
    POSITIVE LOGITS
     zostać
    0.74
     للاسماء
    0.69
     blevet
    0.69
     successfully
    0.69
     thoroughly
    0.68
    会被
    0.66
     verrà
    0.66
     zostało
    0.66
     została
    0.65
     zostanie
    0.65
    Activations Density 0.802%

    No Known Activations