© 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. 9095
    Prev
    Next
    INDEX
    Explanations

    references to remnants, traces, or residues left behind

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

    something is "left" or "remaining"

    np_acts-logits-general · gemini-2.0-flash

    residuals and things left behind

    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
     ویکی‌پدیا
    -0.60
     nahilalakip
    -0.55
    навли
    -0.53
     isInitialized
    -0.53
    Geplaatst
    -0.52
    Personendaten
    -0.50
    pnea
    -0.50
     Sabina
    -0.49
    swire
    -0.49
     lenker
    -0.48
    POSITIVE LOGITS
     residual
    1.66
     leftover
    1.61
     remaining
    1.59
     left
    1.51
     remnants
    1.51
    残
    1.47
     residue
    1.44
    residual
    1.44
    留下
    1.43
     remnant
    1.41
    Activations Density 0.408%

    No Known Activations