Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 6931
    Prev
    Next
    INDEX
    Explanations

    geographic locations and names associated with Michigan

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    KURZBESCHREIBUNG
    -0.88
     propOrder
    -0.86
    Datuak
    -0.85
    Portail
    -0.84
     Efq
    -0.81
     الحره
    -0.79
    onOptions
    -0.79
     noDo
    -0.76
    imothy
    -0.75
     franz
    -0.74
    POSITIVE LOGITS
     Michigan
    0.86
     Detroit
    0.83
     Welsh
    0.80
    Michigan
    0.78
    Detroit
    0.74
     Ukrainian
    0.72
     Coleman
    0.71
     Ukrainians
    0.71
    ROIT
    0.71
    Welsh
    0.68
    Activations Density 0.476%

    No Known Activations