© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 2963
    Prev
    Next
    INDEX
    Explanations

    patterns related to transportation routes and accessibility

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

    Wisconsin or Milwaukee

    np_acts-logits-general · gemini-2.0-flash

    Milwaukee and Wisconsin locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Glasgow
    -0.63
     Pante
    -0.61
    Personendaten
    -0.60
     Rost
    -0.58
     Abuja
    -0.57
     Weir
    -0.57
    PMailer
    -0.56
     Nark
    -0.56
    WebMethod
    -0.56
     Cair
    -0.55
    POSITIVE LOGITS
     Wisconsin
    1.19
    Wisconsin
    1.14
     Milwaukee
    1.07
    Milwaukee
    0.96
     WISCONSIN
    0.95
    consin
    0.86
    CONSIN
    0.85
     Racine
    0.80
     UW
    0.77
    waukee
    0.74
    Activations Density 0.148%

    No Known Activations