© 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. 15-GEMMASCOPE-RES-16K
    11. 5451
    Prev
    Next
    INDEX
    Explanations

    words related to actions and mechanisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erequisite
    -0.76
     Marconi
    -0.75
    তথ্যসূত্র
    -0.73
    stander
    -0.70
    Сообщение
    -0.69
     Einer
    -0.69
     EDP
    -0.68
    Bibliograf
    -0.67
    theless
    -0.67
     gera
    -0.67
    POSITIVE LOGITS
     ACT
    1.41
     Acts
    1.34
     acts
    1.31
     act
    1.30
     Act
    1.28
    ACT
    1.09
     Acton
    1.09
    Acts
    1.09
    Act
    1.06
     acted
    1.05
    Activations Density 0.084%

    No Known Activations