© 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-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 7805
    Prev
    Next
    INDEX
    Explanations

    geographical and historical references related to places and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
     Савезне
    -0.74
    writeField
    -0.73
     ComVisible
    -0.72
    ScopeManager
    -0.71
    aarrggbb
    -0.70
     Wikiseite
    -0.70
    ftagPool
    -0.70
    ロウィン
    -0.69
     otomatig
    -0.69
    EndContext
    -0.68
    POSITIVE LOGITS
     became
    0.35
    後來
    0.34
     was
    0.34
    后来
    0.32
    当时
    0.31
    當時
    0.30
     damals
    0.29
     had
    0.29
     were
    0.28
     later
    0.27
    Activations Density 0.575%

    No Known Activations