© 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. 7-GEMMASCOPE-RES-16K
    11. 14385
    Prev
    Next
    INDEX
    Explanations

    instances of the word "act" along with its variations and related phrases

    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
     Marconi
    -0.89
    তথ্যসূত্র
    -0.80
    erequisite
    -0.75
     Einer
    -0.73
    ایج
    -0.72
     Latimer
    -0.72
    interess
    -0.70
    OMEM
    -0.70
    पया
    -0.70
    Louie
    -0.69
    POSITIVE LOGITS
     act
    1.95
     Act
    1.89
     ACT
    1.87
     Acts
    1.80
     acts
    1.80
    Act
    1.63
    Acts
    1.52
    ACT
    1.50
    act
    1.47
     acted
    1.42
    Activations Density 0.087%

    No Known Activations