© 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. 3244
    Prev
    Next
    INDEX
    Explanations

    repeated occurrences of the word "been" 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
    
    -1.06
     Viceroy
    -0.95
     scissors
    -0.95
     Swat
    -0.91
     Efq
    -0.91
     Lair
    -0.90
     Conscience
    -0.89
     Morro
    -0.89
     ſtate
    -0.86
    rsiniz
    -0.86
    POSITIVE LOGITS
     been
    1.45
     Been
    1.23
    Been
    1.15
     BEEN
    1.00
    been
    0.99
    HasBeen
    0.84
     été
    0.73
    an
    0.73
     an
    0.72
    ")->
    0.69
    Activations Density 0.101%

    No Known Activations