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. 5-GEMMASCOPE-RES-16K
    6. 14177
    Prev
    Next
    INDEX
    Explanations

    sections or mentions related to mathematical proofs and theorems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     szóci
    -0.68
    GEBURTS
    -0.63
    internalType
    -0.60
     CreateTagHelper
    -0.60
    WriteAttribute
    -0.59
    fortawesome
    -0.57
     jadx
    -0.57
     ErrIntOverflow
    -0.56
    compar
    -0.55
     <=",
    -0.55
    POSITIVE LOGITS
     ExecuteAsync
    0.90
    setVerticalGroup
    0.76
    __':
    
    0.66
    Viitteet
    0.65
    :✨
    0.64
    __':
    0.64
    endpush
    0.62
     onCreateView
    0.62
     Réponses
    0.61
    UserScript
    0.61
    Activations Density 0.225%

    No Known Activations