© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 10845
    Prev
    Next
    INDEX
    Explanations

    geographical locations and their associated states or regions

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

    US states and abbreviations

    np_acts-logits-general · gemini-2.0-flash

    US states and 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
     متعلقه
    -0.55
    MLLoader
    -0.55
     виправивши
    -0.54
     @"/
    -0.52
    WebElementEntity
    -0.50
    nonatomic
    -0.50
    Бахар
    -0.48
     trans
    -0.46
     plate
    -0.46
    /*
    -0.46
    POSITIVE LOGITS
     purpoſe
    0.96
     itſelf
    0.89
     Theſe
    0.84
     ſtand
    0.81
     uſed
    0.80
     ſche
    0.79
     Reſ
    0.78
     Anſ
    0.78
     ſeveral
    0.76
     poffible
    0.76
    Activations Density 0.089%

    No Known Activations