© 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. 125136
    Prev
    Next
    INDEX
    Explanations

    mentions of garages and related structures

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

    garage, garbage

    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
    Niels
    -0.40
     pData
    -0.40
     />';
    -0.39
    Segoe
    -0.39
     ITU
    -0.38
     '',
    -0.38
     Crohn
    -0.38
     Jésus
    -0.37
     Hodgkin
    -0.37
    こと
    -0.36
    POSITIVE LOGITS
     garage
    2.03
     Garage
    2.02
    Garage
    1.91
    garage
    1.86
     garages
    1.49
     garagem
    1.36
     garaje
    1.30
     GAR
    1.05
     гара
    0.90
     gar
    0.83
    Activations Density 0.006%

    No Known Activations