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. 2990
    Prev
    Next
    INDEX
    Explanations

    terms related to sports athletes and their physical attributes or statistics

    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
    yarnpkg
    -0.68
    发表于
    -0.63
     feathers
    -0.61
     flit
    -0.60
     wits
    -0.56
    Wire
    -0.53
    wire
    -0.53
    issau
    -0.53
    reactivex
    -0.52
     stings
    -0.51
    POSITIVE LOGITS
    SourceChecksum
    0.81
     mammoth
    0.80
     behe
    0.77
    Massive
    0.75
     massive
    0.74
     bulky
    0.74
     heavyweight
    0.74
    massive
    0.72
     lourd
    0.72
     heavy
    0.70
    Activations Density 0.695%

    No Known Activations