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 - 65k
    5. 17-GEMMASCOPE-RES-65K
    6. 28437
    Prev
    Next
    INDEX
    Explanations

    numerical references, particularly pertaining to scripture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_65k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Datuak
    -1.05
     otomatig
    -0.91
    AndroidJUnit
    -0.91
    NameInMap
    -0.90
    protoimpl
    -0.90
     المعيارى
    -0.88
     оригіналу
    -0.82
     nahilalakip
    -0.82
    sizeCache
    -0.82
    ########.
    -0.82
    POSITIVE LOGITS
    <bos>
    0.47
     Idio
    0.45
    3
    0.44
     Ukra
    0.43
     NIV
    0.42
    1
    0.42
     nicio
    0.41
    ClientRect
    0.41
    2
    0.41
    4
    0.41
    Activations Density 0.016%

    No Known Activations