© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 2320
    Prev
    Next
    INDEX
    Explanations

    temporal markers related to events or descriptions of time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Económica
    -0.44
    cotch
    -0.44
    RectangleBorder
    -0.44
    httphttps
    -0.44
     ecológica
    -0.43
    évaluateur
    -0.42
    化为
    -0.42
    kela
    -0.41
    Actual
    -0.41
     للاسماء
    -0.41
    POSITIVE LOGITS
     cherchés
    0.48
    fjspx
    0.42
     للمعارف
    0.41
     Wikimedijinoj
    0.40
    adaptiveStyles
    0.39
     مشين
    0.39
    ="@+
    0.39
     viewDidLoad
    0.38
     архивлан
    0.38
    Reps
    0.36
    Activations Density 0.749%

    No Known Activations