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. 20-GEMMASCOPE-RES-16K
    6. 2356
    Prev
    Next
    INDEX
    Explanations

    scientific terminology related to calcium signaling and its role in synaptic plasticity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Numbers as reference citations

    np_acts-logits-general · gemini-2.0-flash

    citations and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/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.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     دریافت‌شده
    -0.62
    ddots
    -0.56
    quee
    -0.54
     import
    -0.54
    djangoproject
    -0.53
     createState
    -0.53
    HasBeenSet
    -0.53
     LeBlanc
    -0.52
    MutableLiveData
    -0.51
    ないと
    -0.50
    POSITIVE LOGITS
    __":
    
    0.58
     themſelves
    0.56
     NDEBUG
    0.55
    twimg
    0.54
     Houſe
    0.54
     Euri
    0.53
    __':
    
    0.53
     whoſe
    0.53
     juſt
    0.52
    formik
    0.52
    Activations Density 0.506%

    No Known Activations