© 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. 30010
    Prev
    Next
    INDEX
    Explanations

    phrases related to mining projects and resource extraction

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

    geographic locations and properties

    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
     sentence
    -0.32
     forget
    -0.32
     fact
    -0.31
     def
    -0.30
     ات
    -0.30
     shop
    -0.30
     alto
    -0.30
     word
    -0.29
     scratch
    -0.29
    スパ
    -0.29
    POSITIVE LOGITS
     Infórmanos
    0.57
     Picchu
    0.54
    InSection
    0.54
    RTEX
    0.54
    脚注の使い方
    0.53
    authorised
    0.52
     nakalista
    0.52
     Berufung
    0.52
     komende
    0.52
     region
    0.52
    Activations Density 0.014%

    No Known Activations