Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 2790
    Prev
    Next
    INDEX
    Explanations

    data points related to player statistics in sports

    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
    ########.
    -0.50
     palestra
    -0.49
     Pumpkin
    -0.46
     tacón
    -0.46
     existence
    -0.45
    écnicas
    -0.45
     publicKey
    -0.45
    شد
    -0.44
     EventArgs
    -0.43
    grave
    -0.42
    POSITIVE LOGITS
    @[+][
    0.70
    fjspx
    0.70
    TargetException
    0.68
    InjectAttribute
    0.66
    ContentAlignment
    0.66
    URLException
    0.66
    Vidite
    0.64
     MainAxisSize
    0.64
    下载附件
    0.64
     trafi
    0.63
    Activations Density 0.068%

    No Known Activations