© 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-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 12716
    Prev
    Next
    INDEX
    Explanations

    phrases indicating readiness or intent to act

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Normdatei
    -0.65
     kasarigan
    -0.58
     שוליים
    -0.56
     ujednoznacz
    -0.55
    enumii
    -0.54
     Roskov
    -0.47
    tanleria
    -0.47
     monit
    -0.44
    AndroidJUnit
    -0.44
    日閲覧
    -0.44
    POSITIVE LOGITS
     ready
    0.88
     siap
    0.72
    ready
    0.69
     READY
    0.68
     prepared
    0.66
    Ready
    0.65
     Ready
    0.65
     готовы
    0.63
     آماده
    0.61
     readiness
    0.60
    Activations Density 0.242%

    No Known Activations