© 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-2-9B
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 7373
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to sports statistics and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.58
     AssemblyCulture
    -0.56
    MessageOf
    -0.54
    AutoScaleMode
    -0.53
    dAtA
    -0.46
    KommentareTeilen
    -0.44
     createState
    -0.43
     Azevedo
    -0.42
     Carvalho
    -0.41
    WebElementEntity
    -0.41
    POSITIVE LOGITS
     baseball
    1.39
     MLB
    1.23
     Baseball
    1.22
    Baseball
    1.14
    baseball
    1.10
    MLB
    1.09
     pitchers
    1.02
     pitching
    0.97
    ⚾
    0.96
     pitcher
    0.94
    Activations Density 0.259%

    No Known Activations