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. 12-GEMMASCOPE-RES-16K
    6. 1168
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and equations involving derivatives and powers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Jansen
    -0.61
    ṛ
    -0.60
    ్ర
    -0.57
     Larkin
    -0.57
    drawing
    -0.57
     Therap
    -0.56
     Butt
    -0.56
    noinspection
    -0.55
     Heinrich
    -0.55
     Zen
    -0.55
    POSITIVE LOGITS
     متعلقه
    0.99
    seamnă
    0.91
    المناصب
    0.85
    ValueStyle
    0.85
    onViewCreated
    0.83
     NSCoder
    0.81
    InstanceState
    0.81
    StoryboardSegue
    0.79
    Jeografia
    0.78
     typelib
    0.77
    Activations Density 0.732%

    No Known Activations