© 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. 7-GEMMASCOPE-RES-16K
    6. 13976
    Prev
    Next
    INDEX
    Explanations

    references to downregulation in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Viki
    -1.03
     Magi
    -0.96
    érêt
    -0.84
    FontOfSize
    -0.82
     Winaray
    -0.82
    PhysRev
    -0.82
    ształ
    -0.81
     belangrij
    -0.80
    licet
    -0.78
    NewUrlParser
    -0.78
    POSITIVE LOGITS
     down
    2.02
     Down
    1.97
    Down
    1.92
     DOWN
    1.84
    down
    1.77
    DOWN
    1.68
    downs
    1.56
    Downs
    1.46
     downs
    1.43
     Downs
    1.34
    Activations Density 0.069%

    No Known Activations