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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 15116
    Prev
    Next
    INDEX
    Explanations

    financial statistics and comparisons over different time periods

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

    Quantities with time context

    np_acts-logits-general · gemini-2.0-flash

    quantities compared year over year

    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
     ISNI
    -0.60
     خارجية
    -0.56
    aste
    -0.54
    Xna
    -0.53
     tartalomajánló
    -0.48
    หาร
    -0.46
    ității
    -0.45
    stens
    -0.45
    싸
    -0.45
    أة
    -0.45
    POSITIVE LOGITS
    Datuak
    0.74
     previous
    0.74
     corresponding
    0.73
     prior
    0.72
     годом
    0.72
    省市镇
    0.71
    Geplaatst
    0.71
    corresponding
    0.70
    دانشنامهٔ
    0.69
     disambiguazione
    0.68
    Activations Density 0.127%

    No Known Activations