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. 22-GEMMASCOPE-RES-16K
    6. 12797
    Prev
    Next
    INDEX
    Explanations

    references to graduation events and associated celebrations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    graduations or graduates

    np_acts-logits-general · gemini-2.0-flash

    school graduation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     متعلقه
    -0.91
     الحره
    -0.81
     AssemblyTitle
    -0.76
    Autoritní
    -0.76
     linkovi
    -0.76
    DebuggerNonUser
    -0.71
    kháu
    -0.69
     gọn
    -0.69
    rungsseite
    -0.68
    Tembelea
    -0.68
    POSITIVE LOGITS
     graduates
    1.85
     graduating
    1.81
     graduation
    1.72
     graduated
    1.59
     Graduates
    1.58
     graduate
    1.54
    Gradu
    1.53
     grads
    1.50
     gradu
    1.45
     Gradu
    1.43
    Activations Density 0.135%

    No Known Activations