Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 8220
    Prev
    Next
    INDEX
    Explanations

    references to time and future projections in various contexts

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

    time: "immediate", "term", "year", or "now"

    np_acts-logits-general · gemini-2.0-flash

    immediate and in the future

    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
     resourceCulture
    -0.37
    Derbyniad
    -0.36
     بک
    -0.32
     setObject
    -0.31
     jackson
    -0.30
    #!/
    -0.30
     valueOf
    -0.29
     english
    -0.28
     nahilalakip
    -0.28
    albero
    -0.28
    POSITIVE LOGITS
     للمعارف
    0.73
     inmediata
    0.66
    immediate
    0.65
     immediate
    0.64
     Immediate
    0.64
    Immediate
    0.62
    Hiện
    0.60
    ImageContext
    0.59
    transQ
    0.59
     현재
    0.57
    Activations Density 0.442%

    No Known Activations