© 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. 31-GEMMASCOPE-RES-131K
    11. 10126
    Prev
    Next
    INDEX
    Explanations

    references to groups or collectives, particularly cliques or clans

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

    clan, Clarence, clang, sect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.57
    DotNetBar
    -0.53
    发表于
    -0.53
     المعيارى
    -0.52
     otomatig
    -0.52
    awtextra
    -0.50
     referrerpolicy
    -0.49
     noDo
    -0.47
     kaarangay
    -0.46
     للمعارف
    -0.46
    POSITIVE LOGITS
     Clan
    0.78
    Clan
    0.77
     clan
    0.69
    clan
    0.65
     clans
    0.59
     Clans
    0.58
     Clancy
    0.57
     MongoClient
    0.50
    族
    0.47
    Tribal
    0.46
    Activations Density 0.004%

    No Known Activations