© 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. 20-GEMMASCOPE-RES-16K
    11. 2494
    Prev
    Next
    INDEX
    Explanations

    references to measurements and weighing scales

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

    scales or weighing items

    np_acts-logits-general · gemini-2.0-flash

    scales and weighing

    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
    AndEndTag
    -0.70
    ErrUnexpectedEOF
    -0.64
    afficheront
    -0.62
     OFDb
    -0.62
     propOrder
    -0.59
    HtmlAttribute
    -0.58
    lankton
    -0.55
     dAtA
    -0.55
     Paglinawan
    -0.54
     intStringLen
    -0.53
    POSITIVE LOGITS
     scales
    2.24
     scale
    2.04
     Scales
    2.04
     Scale
    1.90
    scales
    1.82
    scale
    1.70
    Scale
    1.70
    Scales
    1.67
     balance
    1.66
     SCALE
    1.63
    Activations Density 0.182%

    No Known Activations