© 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. 17-GEMMASCOPE-RES-16K
    6. 10561
    Prev
    Next
    INDEX
    Explanations

    references to a specific concept or entity related to "fa."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/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.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Huston
    -0.60
     BorderLayout
    -0.59
    addImage
    -0.56
     العنوان
    -0.56
     utili
    -0.56
    Ārējās
    -0.56
    vinte
    -0.56
    express
    -0.55
    ROSS
    -0.55
    typeorm
    -0.55
    POSITIVE LOGITS
     fa
    1.01
     Fa
    0.93
    fa
    0.82
    Fa
    0.79
     Faz
    0.71
     Fai
    0.71
     faw
    0.71
     FA
    0.70
    Faz
    0.69
     Faw
    0.65
    Activations Density 0.149%

    No Known Activations