© 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. 9342
    Prev
    Next
    INDEX
    Explanations

    neutrals or terms without significant activation signals

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

    Code, URLs, or file paths

    np_acts-logits-general · gemini-2.0-flash

    Chinese judges

    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
    issante
    -0.46
    <eos>
    -0.44
     “
    -0.43
    ’
    -0.42
    doctype
    -0.42
    ↵↵
    -0.42
      
    -0.41
     No
    -0.41
     
    -0.41
     dasar
    -0.41
    POSITIVE LOGITS
    uxxxx
    0.90
     houſe
    0.73
     AppColors
    0.72
     ſche
    0.69
     الحره
    0.69
     ſind
    0.67
    Datuak
    0.67
    ſelves
    0.66
     faſt
    0.66
     Mémoires
    0.66
    Activations Density 0.012%

    No Known Activations