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. 25-GEMMASCOPE-RES-16K
    6. 8581
    Prev
    Next
    INDEX
    Explanations

    phrases related to design and functionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    writeFieldEnd
    -0.68
    expandindo
    -0.65
     createState
    -0.64
    setof
    -0.63
     otomatig
    -0.61
     MaterialApp
    -0.61
     betweenstory
    -0.59
     Signalez
    -0.59
    ThroughAttribute
    -0.57
    IVEREF
    -0.55
    POSITIVE LOGITS
     specifically
    1.75
    specifically
    1.49
     expressly
    1.39
     specially
    1.34
     especially
    1.32
     spécialement
    1.31
     Specifically
    1.29
     специально
    1.29
     específicamente
    1.29
    Specifically
    1.28
    Activations Density 0.384%

    No Known Activations