© 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 - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 6130
    Prev
    Next
    INDEX
    Explanations

    geographical names and locations, particularly in relation to regions in Scotland and Connecticut

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

    Geographic locations or place names

    np_acts-logits-general · gemini-2.0-flash

    place names

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     nakalista
    -0.52
    awakeFromNib
    -0.51
    urlpatterns
    -0.50
     betweenstory
    -0.48
    twimg
    -0.47
    HandleFunc
    -0.47
    IBOutlet
    -0.47
     defaultstate
    -0.46
     ProtoMessage
    -0.45
    httphttps
    -0.44
    POSITIVE LOGITS
     ferry
    0.56
     Dhabi
    0.50
    Ferry
    0.48
     Bratislava
    0.47
    ArrowToggle
    0.46
     Bahrain
    0.46
    Niagara
    0.46
    ratislava
    0.46
     Danube
    0.45
    Bahrain
    0.45
    Activations Density 0.606%

    No Known Activations