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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 338
    Prev
    Next
    INDEX
    Explanations

    mentions of memory

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    первых
    -0.61
     estimés
    -0.60
    Lähteet
    -0.56
    setDo
    -0.52
    Whom
    -0.52
     độ
    -0.50
    (;;)
    -0.50
    fonts
    -0.50
    니다
    -0.48
     dotyczące
    -0.48
    POSITIVE LOGITS
     memory
    0.94
    存于互联网档案馆
    0.90
    OGND
    0.89
    memory
    0.78
     oprot
    0.77
     utafitiHapana
    0.77
     Memory
    0.75
    INSEE
    0.74
     memories
    0.72
     MEMORY
    0.69
    Activations Density 0.183%

    No Known Activations