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. 15-GEMMASCOPE-RES-16K
    6. 2474
    Prev
    Next
    INDEX
    Explanations

    words related to sacrificial practices and longevity in religious or cultural contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Carriera
    -0.60
    μμ
    -0.54
    DIPSETTING
    -0.50
    sizeCache
    -0.48
     oocytes
    -0.47
    jgl
    -0.47
     keber
    -0.46
    __":
    
    -0.46
     salarios
    -0.46
    Rè
    -0.45
    POSITIVE LOGITS
     BoxFit
    0.68
    +#+#
    0.67
     مشين
    0.65
     TimeUnit
    0.64
    AutoresizingMask
    0.62
     nawr
    0.60
    เหล
    0.58
    resaid
    0.58
     الرياضيه
    0.57
     متعلقه
    0.56
    Activations Density 0.752%

    No Known Activations