© 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-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 11508
    Prev
    Next
    INDEX
    Explanations

    technical terms and specifications related to computer hardware and architecture

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

    Numbers followed by units or specifications

    np_acts-logits-general · gemini-2.0-flash

    Intel CPUs and Windows

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     iPod
    -0.69
     Macintosh
    -0.64
    berdayakan
    -0.63
     ipod
    -0.60
    :].
    -0.59
     Mubarak
    -0.59
    :]:
    -0.58
     MySpace
    -0.57
    iPod
    -0.57
    Wii
    -0.57
    POSITIVE LOGITS
    MENAFN
    0.62
    Personensuche
    0.61
     RTX
    0.61
    reactstrap
    0.61
     rtx
    0.59
    rtx
    0.52
    ItemLayout
    0.50
    <>();
    
    0.49
    onViewCreated
    0.49
    RestController
    0.46
    Activations Density 0.108%

    No Known Activations