© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 14809
    Prev
    Next
    INDEX
    Explanations

    code syntax and structures related to programming or scripting

    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
    ↵↵
    -0.51
     
    -0.50
    )}(\
    -0.50
     "
    -0.49
    ())).
    -0.49
    <eos>
    -0.48
     “
    -0.46
    )}^{
    -0.46
     #
    -0.46
    ís
    -0.45
    POSITIVE LOGITS
     ―――――
    0.69
     FetchType
    0.68
    inander
    0.68
     cherchés
    0.66
    forRoot
    0.65
     vectorstock
    0.64
    itattu
    0.62
    المناصب
    0.62
    glGen
    0.61
     photolibrary
    0.61
    Activations Density 0.432%

    No Known Activations