© 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. 10-GEMMASCOPE-RES-16K
    11. 3231
    Prev
    Next
    INDEX
    Explanations

    references to low or reduced values 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 @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     virtù
    -0.84
     Mundi
    -0.80
    GOTREF
    -0.80
    WireFormatLite
    -0.78
     supérieurs
    -0.77
     véhic
    -0.77
     européennes
    -0.77
     financières
    -0.76
     détru
    -0.76
     servici
    -0.75
    POSITIVE LOGITS
     LOW
    1.67
     Low
    1.64
     low
    1.60
    Low
    1.49
     Lowry
    1.42
    low
    1.32
    LOW
    1.22
     Lowe
    1.17
     lows
    1.15
    低
    1.14
    Activations Density 0.105%

    No Known Activations