© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 11135
    Prev
    Next
    INDEX
    Explanations

    names of places and legal terms related to zoning and property law

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

    Michigan and Detroit

    np_acts-logits-general · gemini-2.0-flash

    Michigan cities and legal citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
    PageModule
    -0.40
     henvisninger
    -0.38
    Grá
    -0.36
    vbox
    -0.35
     cross
    -0.32
     smo
    -0.32
     Gree
    -0.31
     plait
    -0.31
    FormsModule
    -0.30
     stream
    -0.30
    POSITIVE LOGITS
     Detroit
    1.10
    Detroit
    1.09
     DETROIT
    1.02
    Michigan
    0.99
     Michigan
    0.99
    detroit
    0.92
     MICHIGAN
    0.92
    ROIT
    0.85
    higan
    0.69
    ymce
    0.68
    Activations Density 0.350%

    No Known Activations