© 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. 12019
    Prev
    Next
    INDEX
    Explanations

    specific tokens representing data values or codes, likely related to computational contexts

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

    Hexadecimal representations of currency codes

    np_acts-logits-general · gemini-2.0-flash

    names following periods

    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
    apat
    -0.56
    onin
    -0.52
    arsal
    -0.49
     other
    -0.48
    liziert
    -0.48
    Resumen
    -0.47
    uro
    -0.47
     anges
    -0.46
    orthy
    -0.46
     ar
    -0.46
    POSITIVE LOGITS
     calendriers
    0.85
     &___
    0.81
     CreateTagHelper
    0.71
    :✨
    0.66
     Administrativna
    0.64
    tagHelper
    0.63
     viewDidLoad
    0.63
     surla
    0.63
     nakalista
    0.63
    MENAFN
    0.63
    Activations Density 0.173%

    No Known Activations