© 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. 16-GEMMASCOPE-RES-16K
    11. 4902
    Prev
    Next
    INDEX
    Explanations

    specific numeric values and date-related references

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

    years

    np_acts-logits-general · gemini-2.0-flash

    years and dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bondi
    -0.57
    akaian
    -0.56
     نما
    -0.50
     obed
    -0.50
     Shakspeare
    -0.49
     Fod
    -0.49
     viad
    -0.49
     Marry
    -0.49
     synap
    -0.49
    culin
    -0.49
    POSITIVE LOGITS
    enumi
    0.76
    setVerticalGroup
    0.75
     predeceased
    0.74
    BeginContext
    0.72
     فريبيس
    0.70
    expandindo
    0.66
    MemoryWarning
    0.64
     насељу
    0.64
    providedIn
    0.64
     jScrollPane
    0.59
    Activations Density 0.091%

    No Known Activations