© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 5548
    Prev
    Next
    INDEX
    Explanations

    terms associated with buying and selling activities, particularly in economic contexts

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

    riots, curfew, and disturbances

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     InputDecoration
    -0.46
     académica
    -0.45
    
    -0.45
     inalámbrica
    -0.45
    setupUi
    -0.44
     onderhoud
    -0.43
     مشين
    -0.43
    seat
    -0.43
    ugou
    -0.42
    endt
    -0.42
    POSITIVE LOGITS
     autorytatywna
    0.48
     panic
    0.48
     rationing
    0.48
     tartalomajánló
    0.42
     Panic
    0.41
     riots
    0.41
     grocery
    0.40
     pande
    0.40
     unknownFields
    0.40
    awtextra
    0.40
    Activations Density 0.124%

    No Known Activations