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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 12264
    Prev
    Next
    INDEX
    Explanations

    elements of Australian culture in various contexts

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

    Text following a sentence

    np_acts-logits-general · gemini-2.0-flash

    Australian speculative fiction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/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.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NewUrlParser
    -0.76
     Majefty
    -0.67
    paravant
    -0.66
     nonUne
    -0.66
    oretical
    -0.64
    Zeneca
    -0.63
    enerys
    -0.62
    发表于
    -0.62
     Houſe
    -0.62
     tisch
    -0.61
    POSITIVE LOGITS
     Watching
    0.68
    Watching
    0.68
     there
    0.67
    Overall
    0.66
     enjoyable
    0.61
    全体的に
    0.60
     Overall
    0.59
    there
    0.58
     it
    0.57
     really
    0.57
    Activations Density 0.178%

    No Known Activations