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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 8-GEMMASCOPE-RES-16K
    6. 8114
    Prev
    Next
    INDEX
    Explanations

    elements related to memory and identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     שוליים
    -0.71
     twain
    -0.69
    Obrázky
    -0.60
    yszer
    -0.57
     typelib
    -0.57
     Duma
    -0.56
     pleaſure
    -0.55
     anſ
    -0.55
     OFDb
    -0.54
    omock
    -0.53
    POSITIVE LOGITS
     lost
    0.62
     Lost
    0.62
    lost
    0.61
     natural
    0.58
    Lost
    0.56
    LOST
    0.56
     redis
    0.55
    MENAFN
    0.55
     Natural
    0.54
     reconnect
    0.54
    Activations Density 0.300%

    No Known Activations