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. 8-GEMMASCOPE-RES-16K
    6. 14875
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports awards and recognitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.58
     beſ
    -0.58
     raiſ
    -0.57
     neceſſ
    -0.56
     HasFactory
    -0.54
    (!__
    -0.53
     purpoſe
    -0.53
     ſur
    -0.53
     fièvre
    -0.53
    ſelves
    -0.53
    POSITIVE LOGITS
    writeFieldEnd
    0.70
    rawDesc
    0.56
    utilisons
    0.55
    elfde
    0.55
     onResponse
    0.55
    posób
    0.54
    toolkit
    0.54
     vendus
    0.53
    dientemente
    0.51
    NOPQRST
    0.49
    Activations Density 0.133%

    No Known Activations