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. 12-GEMMASCOPE-RES-65K
    6. 36579
    Prev
    Next
    INDEX
    Explanations

    terms related to redistribution and testing in software contexts

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    rrggbb
    -0.66
     sanitaires
    -0.63
     Beecher
    -0.60
     concernés
    -0.59
    melidir
    -0.59
     indépend
    -0.58
     élevées
    -0.56
     publiques
    -0.55
     Zwiebel
    -0.55
     ujednoznacz
    -0.54
    POSITIVE LOGITS
    openConnection
    1.01
    zzleHttp
    0.90
     CreateTagHelper
    0.85
    Personensuche
    0.82
    mvc
    0.80
    pushFollow
    0.77
    Datuak
    0.77
    tinyos
    0.74
     numerus
    0.73
    CORBA
    0.72
    Activations Density 0.001%

    No Known Activations