© 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. 20-GEMMASCOPE-RES-16K
    11. 2026
    Prev
    Next
    INDEX
    Explanations

    phrases indicating emotional or social tension

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    complex language describing emotional or analytical states, particularly involving subjective assessments or personal perspectives.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.78
    \{\\
    -0.66
    الحياه
    -0.63
     noDo
    -0.62
    ScopeManager
    -0.61
    InitVars
    -0.61
     الرياضيه
    -0.60
    
    -0.59
     ujednoznacz
    -0.59
     برانيه
    -0.58
    POSITIVE LOGITS
     banget
    0.47
    非常好
    0.46
     للغاية
    0.45
     indeed
    0.41
     Bardzo
    0.41
     Very
    0.41
    VERY
    0.40
    Very
    0.40
    Bardzo
    0.39
     very
    0.37
    Activations Density 0.614%

    No Known Activations