© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 20784
    Prev
    Next
    INDEX
    Explanations

    negative or diminishing terms that indicate problems or issues

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

    adjuvants, recalcitrant, obsoleted

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pérd
    -0.71
     anún
    -0.66
     mercancías
    -0.65
     Gegenteil
    -0.65
    mejores
    -0.64
     regalías
    -0.63
     desnuda
    -0.61
     Infór
    -0.61
     ainfi
    -0.60
     zboží
    -0.60
    POSITIVE LOGITS
    xnn
    0.56
    躇
    0.56
    AxisAlignment
    0.55
     FontWeight
    0.55
    {~
    0.55
    Pyx
    0.54
    wapV
    0.53
    [toxicity=0]
    0.52
    zzleHttp
    0.52
    ThemeOverlay
    0.51
    Activations Density 0.219%

    No Known Activations