© 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. 6933
    Prev
    Next
    INDEX
    Explanations

    references to 'the' along with changes in context

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

    After "the" in diverse contexts

    np_acts-logits-general · gemini-2.0-flash

    the leap

    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
    pios
    -0.48
     tenuto
    -0.45
    ficamente
    -0.45
     Emits
    -0.44
    ginfo
    -0.43
     superiore
    -0.42
    aarrggbb
    -0.42
    WRP
    -0.42
     aquilo
    -0.42
     those
    -0.42
    POSITIVE LOGITS
     ffilmiau
    0.81
    AddTagHelper
    0.78
     blame
    0.76
     NSCoder
    0.68
     conversation
    0.67
    blame
    0.67
    Fordítás
    0.67
     disambiguazione
    0.66
    NewUrlParser
    0.65
     AssemblyCulture
    0.65
    Activations Density 0.359%

    No Known Activations