Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 31580
    Prev
    Next
    INDEX
    Explanations

    references to ordered sets or tuples in mathematical contexts

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

    ordered pairs and triples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Geografia
    -0.44
    ApiException
    -0.40
     خارجية
    -0.39
    Schweiz
    -0.38
    Vidite
    -0.38
     tambahan
    -0.38
    ribusi
    -0.37
     Fernsehen
    -0.36
     enx
    -0.36
    getSystemService
    -0.36
    POSITIVE LOGITS
    Ordered
    1.84
    ordered
    1.80
     Ordered
    1.73
     ordered
    1.72
     ordering
    1.66
     Ordering
    1.63
    ordering
    1.54
    Ordering
    1.50
     ORDERED
    1.42
    有序
    1.15
    Activations Density 0.014%

    No Known Activations