© 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. 20-GEMMASCOPE-RES-16K
    11. 255
    Prev
    Next
    INDEX
    Explanations

    locations and geographic names

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

    Start of place names

    np_acts-logits-general · gemini-2.0-flash

    geographical names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     
    -0.54
     rekening
    -0.54
    年も
    -0.52
     final
    -0.51
    FieldBuilder
    -0.50
    STARS
    -0.50
     once
    -0.49
     good
    -0.48
    premi
    -0.48
     online
    -0.48
    POSITIVE LOGITS
     StatelessWidget
    0.74
     AllAfrica
    0.69
     IBOutlet
    0.67
    MfG
    0.63
     MCQ
    0.62
     FEC
    0.61
     MonoBehaviour
    0.61
     CURIAM
    0.60
     equalizer
    0.59
    ="{{$
    0.57
    Activations Density 0.240%

    No Known Activations