© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 10744
    Prev
    Next
    INDEX
    Explanations

    mentions of notable collaborations and commitments to the arts

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

    Australian locations or entities

    np_acts-logits-general · gemini-2.0-flash

    Australia and Australian places

    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
    慳
    -0.81
    餸
    -0.61
    糅
    -0.59
    賬
    -0.58
    報道
    -0.58
    ReusableCell
    -0.57
    捱
    -0.57
    凈
    -0.56
    嬲
    -0.55
    
    -0.55
    POSITIVE LOGITS
     Pty
    1.47
     Australian
    1.46
     Australia
    1.43
     Melbourne
    1.41
    Australian
    1.39
     Brisbane
    1.39
     Australians
    1.39
     Queensland
    1.37
     Canberra
    1.35
     CSIRO
    1.34
    Activations Density 0.618%

    No Known Activations