© 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
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 10968
    Prev
    Next
    INDEX
    Explanations

    variations of the verb "be" in different tenses and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Мексичка
    -0.41
    knowing
    -0.38
    現在は
    -0.37
    謗
    -0.36
     knowing
    -0.36
     arvio
    -0.35
    Itoa
    -0.34
    Geografi
    -0.34
     figlia
    -0.34
    IgnoreCase
    -0.34
    POSITIVE LOGITS
     available
    0.75
     here
    0.67
     disponible
    0.62
     joining
    0.62
     EconPapers
    0.62
    available
    0.61
     AVAILABLE
    0.60
    AVAILABLE
    0.56
     Joining
    0.56
     Available
    0.55
    Activations Density 0.245%

    No Known Activations