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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10006
    Prev
    Next
    INDEX
    Explanations

    numeric values or counts

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

    Following "to," "I," or "get"

    np_acts-logits-general · gemini-2.0-flash

    finally decided finishing procrastinating

    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
     suffit
    -0.67
     verrez
    -0.66
     indipendente
    -0.65
     yourselves
    -0.63
     automaticamente
    -0.62
    あなたが
    -0.59
     tră
    -0.59
     zichzelf
    -0.59
     automáticamente
    -0.58
     quæ
    -0.58
    POSITIVE LOGITS
     finally
    0.79
    finally
    0.73
     FINALLY
    0.71
     procrastin
    0.68
     forgot
    0.64
     tonight
    0.63
     experimenting
    0.62
     Finally
    0.62
     Decided
    0.60
     finishing
    0.60
    Activations Density 0.367%

    No Known Activations