© 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-2-2B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 4444
    Prev
    Next
    INDEX
    Explanations

    quantities or measurements, particularly related to averages and rates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     esto
    -0.49
     CHtml
    -0.49
    getItemId
    -0.48
     Toh
    -0.46
     façons
    -0.45
    }{*}{
    -0.44
    โท
    -0.43
    list
    -0.43
    UMENT
    -0.43
     remettre
    -0.43
    POSITIVE LOGITS
     متعلقه
    1.03
    Chaque
    0.99
    IUrlHelper
    0.98
     every
    0.91
    every
    0.89
    EACH
    0.88
     chaque
    0.87
     annum
    0.86
    AutoScaleMode
    0.86
    Демографія
    0.85
    Activations Density 0.125%

    No Known Activations