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. 21-GEMMASCOPE-RES-16K
    6. 2099
    Prev
    Next
    INDEX
    Explanations

    numerical data, especially those related to quantities or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Amongst
    -0.50
     Among
    -0.49
    missione
    -0.48
    raire
    -0.46
     tutela
    -0.45
     آورد
    -0.45
     خدمت
    -0.44
     취
    -0.44
    isel
    -0.43
    ,
    -0.43
    POSITIVE LOGITS
    новниш
    0.87
     препратки
    0.85
     '\\;'
    0.78
    ########.
    0.78
    AccessorTable
    0.78
     disambiguazione
    0.77
    Personendaten
    0.75
     tartalomajánló
    0.71
    verwijspagina
    0.70
     bParam
    0.70
    Activations Density 0.358%

    No Known Activations