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. 10-GEMMASCOPE-RES-16K
    6. 4319
    Prev
    Next
    INDEX
    Explanations

    events related to sports statistics and outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TagMode
    -1.25
     referenties
    -1.05
    parsedMessage
    -1.02
    ########.
    -0.90
    ValueStyle
    -0.88
     Савезне
    -0.85
    зулта
    -0.84
     defaultstate
    -0.84
    FailureListener
    -0.81
     AssemblyCulture
    -0.81
    POSITIVE LOGITS
    cest
    0.52
    ما
    0.51
     revis
    0.50
     revisit
    0.49
     previously
    0.46
    file
    0.43
     koll
    0.41
    vento
    0.41
     ta
    0.41
     return
    0.41
    Activations Density 0.190%

    No Known Activations