© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 14850
    Prev
    Next
    INDEX
    Explanations

    phrases associated with performance metrics and trends, particularly in sports contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èdia
    -0.67
     utafitiHapana
    -0.60
    /***/
    -0.59
    Décès
    -0.59
    TagMode
    -0.55
    Composable
    -0.54
    Slf
    -0.53
    ))]
    -0.51
    Geplaatst
    -0.51
    утбо
    -0.50
    POSITIVE LOGITS
     epidemic
    0.72
     StringTokenizer
    0.70
     craze
    0.70
     spurt
    0.70
    FieldBuilder
    0.69
    streak
    0.68
     streak
    0.68
     boom
    0.67
     resurgence
    0.67
     outbreak
    0.67
    Activations Density 0.402%

    No Known Activations