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. 15-GEMMASCOPE-RES-16K
    6. 12495
    Prev
    Next
    INDEX
    Explanations

    phrases related to transactions and submissions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     editados
    -0.42
     légale
    -0.38
     hers
    -0.37
    viewBox
    -0.37
     vê
    -0.37
    biol
    -0.36
     naar
    -0.35
     capítulos
    -0.35
    tand
    -0.34
     Commerce
    -0.34
    POSITIVE LOGITS
    RegressionTest
    0.84
    Datuak
    0.79
     >=",
    0.78
     kasarigan
    0.70
     يتيمه
    0.69
     CreateTagHelper
    0.68
     Wikimedijinoj
    0.67
    لينكات
    0.66
    */),
    0.66
    enumii
    0.65
    Activations Density 0.777%

    No Known Activations