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. 1-GEMMASCOPE-RES-16K
    6. 6174
    Prev
    Next
    INDEX
    Explanations

    references to innings in a baseball context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     saites
    -0.62
    υμ
    -0.56
    /***/
    -0.56
    XmlAccessType
    -0.56
     lack
    -0.55
    glVertex
    -0.53
    colades
    -0.52
     lacks
    -0.51
    Conc
    -0.51
    ступила
    -0.51
    POSITIVE LOGITS
     innings
    2.17
     inning
    2.09
    inning
    1.37
    就
    0.79
    EndInit
    0.69
     就
    0.68
     Messenger
    0.68
    الإنجليزية
    0.65
    ValueStyle
    0.65
     الاطلاع
    0.62
    Activations Density 0.082%

    No Known Activations