© 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. 8-GEMMASCOPE-RES-16K
    11. 3518
    Prev
    Next
    INDEX
    Explanations

    terms related to fixing and correcting issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/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.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    new
    -0.39
     yür
    -0.39
    Life
    -0.37
     marad
    -0.37
    ath
    -0.37
    annin
    -0.37
     dehydrated
    -0.36
    мика
    -0.35
    лерея
    -0.35
     sapiens
    -0.35
    POSITIVE LOGITS
     corrects
    0.97
    Fixes
    0.97
     correcting
    0.90
     solves
    0.89
     corregir
    0.86
     solucionar
    0.86
     rectify
    0.86
     remedied
    0.86
     solved
    0.85
     solve
    0.84
    Activations Density 0.532%

    No Known Activations