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. 19-GEMMASCOPE-RES-16K
    6. 3041
    Prev
    Next
    INDEX
    Explanations

    phrases related to teams and coaching situations 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 @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InputTagHelper
    -0.53
     dile
    -0.52
    BufferException
    -0.48
    !*\
    -0.48
     disponibilités
    -0.47
    มาะ
    -0.45
     ostavi
    -0.44
    OND
    -0.44
     calme
    -0.43
     Reichstag
    -0.42
    POSITIVE LOGITS
     coach
    1.03
    Coach
    0.86
     Coach
    0.86
     director
    0.74
    coach
    0.74
    AndEndTag
    0.71
     Director
    0.70
    導演
    0.67
    Director
    0.65
    celotti
    0.65
    Activations Density 0.128%

    No Known Activations