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. 1-GEMMASCOPE-RES-16K
    6. 9557
    Prev
    Next
    INDEX
    Explanations

    mentions of the state of Georgia

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Przypisy
    -0.71
    amssymb
    -0.65
     Roskov
    -0.60
    invokeLater
    -0.60
    vados
    -0.59
    awtextra
    -0.59
    makeConstraints
    -0.58
    Frequent
    -0.56
    ösung
    -0.56
    requent
    -0.56
    POSITIVE LOGITS
     Georgia
    2.02
    Georgia
    1.87
     GEORGIA
    1.61
     georgia
    1.47
     GA
    1.46
     Ga
    1.45
     Georgian
    1.35
     Atlanta
    1.31
    Ga
    1.19
    georg
    1.17
    Activations Density 0.081%

    No Known Activations