© 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. 126247
    Prev
    Next
    INDEX
    Explanations

    references to configuration details and parameters in code, particularly related to the "ngx" or HTTP context

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

    Nginx probes

    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
    tvguidetime
    -0.57
    subsubsection
    -0.55
     nakalista
    -0.51
     ſind
    -0.47
    তথ্যসূত্র
    -0.44
     xrange
    -0.44
    subsection
    -0.43
     oignons
    -0.40
    Electronic
    -0.40
     (\<
    -0.39
    POSITIVE LOGITS
     Administrativna
    0.63
     createState
    0.63
    NewLabel
    0.62
    medriver
    0.61
    inalg
    0.60
     Савезне
    0.58
    ieteur
    0.57
    lgari
    0.56
    enumi
    0.55
    ghijklmnop
    0.55
    Activations Density 0.149%

    No Known Activations