© 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. 2106
    Prev
    Next
    INDEX
    Explanations

    concepts related to classification and data analysis processes

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

    data processing steps

    np_acts-logits-general · gemini-2.0-flash

    classification, conditioning, filtering, verification, quantification, categorization, adaptation

    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
     numberWith
    -0.58
    olyn
    -0.53
    ValueGenerated
    -0.52
    ContextHolder
    -0.50
     egg
    -0.50
    windowFixed
    -0.49
     Truth
    -0.49
     équilibr
    -0.48
    odles
    -0.48
    ylvan
    -0.47
    POSITIVE LOGITS
     done
    0.94
     process
    0.85
    done
    0.81
     dilakukan
    0.80
     procedure
    0.79
     of
    0.78
     efforts
    0.77
     Done
    0.77
     ulang
    0.76
     procedures
    0.74
    Activations Density 1.363%

    No Known Activations