© 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. 8240
    Prev
    Next
    INDEX
    Explanations

    references to specific products and services, particularly in a retail or online marketplace context

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

    スリーパー、オーディオ、ラブ、ブローカー

    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
     zijne
    -0.53
     istrinya
    -0.53
     keben
    -0.52
     suaminya
    -0.52
     fédé
    -0.51
     ibunya
    -0.49
     creencias
    -0.49
     Behör
    -0.47
     órg
    -0.46
     quaisquer
    -0.44
    POSITIVE LOGITS
     بيها
    0.62
    لينكات
    0.61
     bres
    0.60
    dass
    0.60
     ſur
    0.59
     EXCEL
    0.59
    المكان
    0.58
    WAM
    0.58
     SRM
    0.58
     PIA
    0.57
    Activations Density 0.011%

    No Known Activations