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. 23-GEMMASCOPE-RES-16K
    6. 5622
    Prev
    Next
    INDEX
    Explanations

    individual player statistics or performance metrics 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 @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InstanceState
    -0.54
    GeneratedValue
    -0.40
     disponibilité
    -0.40
     trono
    -0.40
    code
    -0.39
     Suivez
    -0.38
     souten
    -0.38
     doInBackground
    -0.37
     trhu
    -0.37
     eccl
    -0.37
    POSITIVE LOGITS
     center
    1.29
     forward
    1.22
     centre
    1.15
     guard
    1.09
     defender
    1.06
     defensive
    1.02
     midfielder
    1.01
     catcher
    1.01
     linebacker
    1.01
     defense
    1.00
    Activations Density 0.218%

    No Known Activations