© 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 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. 15184
    Prev
    Next
    INDEX
    Explanations

    concepts related to progress and setbacks

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

    backward movement or regression

    np_acts-logits-general · gemini-2.0-flash

    regress, revert, rollback

    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
     onItemClick
    -0.67
    uesia
    -0.64
     immort
    -0.55
     panoramique
    -0.54
    amaran
    -0.54
    GeneratedValue
    -0.52
     endfor
    -0.52
    mating
    -0.52
     gneiss
    -0.51
    antiation
    -0.51
    POSITIVE LOGITS
     regress
    1.37
     regression
    1.30
     backwards
    1.14
     backward
    1.10
     reg
    1.09
    regression
    1.06
     retro
    1.04
     retrograde
    1.02
     reverted
    1.02
     revert
    1.00
    Activations Density 0.191%

    No Known Activations