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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 1005
    Prev
    Next
    INDEX
    Explanations

    references to video content and social media engagement

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

    Currency symbols and numbers

    np_acts-logits-general · gemini-2.0-flash

    YouTube vlog video uploads

    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
     chóng
    -0.49
     osserv
    -0.48
     condamné
    -0.47
    vânt
    -0.46
    mailto
    -0.45
     HasFactory
    -0.45
    ymce
    -0.45
     것이다
    -0.44
     observación
    -0.43
     = 
    -0.43
    POSITIVE LOGITS
     vlog
    1.00
     videos
    0.90
     YouTuber
    0.86
    vlog
    0.83
     youtuber
    0.83
    MemoryWarning
    0.77
     vids
    0.74
     video
    0.74
     YouTube
    0.71
    videos
    0.71
    Activations Density 0.142%

    No Known Activations