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-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 7932
    Prev
    Next
    INDEX
    Explanations

    references to athletes and their sporting activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erializer
    -0.39
    ValueGenerated
    -0.38
    脚注の使い方
    -0.37
    utilisons
    -0.36
     FetchType
    -0.36
    esModule
    -0.35
    évaluateur
    -0.35
    £
    -0.33
    ViewImports
    -0.33
    iettivo
    -0.32
    POSITIVE LOGITS
     tennis
    1.73
     golf
    1.72
     basketball
    1.59
     badminton
    1.56
     soccer
    1.55
     rugby
    1.55
     volleyball
    1.53
     golfing
    1.51
     hockey
    1.51
    golf
    1.48
    Activations Density 0.614%

    No Known Activations