Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 1-GEMMASCOPE-RES-16K
    6. 9498
    Prev
    Next
    INDEX
    Explanations

    political affiliations and changes in party membership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.59
    ublik
    -0.56
    ATIV
    -0.55
    rungsseite
    -0.53
     tids
    -0.52
    virons
    -0.51
     تضيفلها
    -0.51
    Blazor
    -0.51
    ISODE
    -0.50
    USAL
    -0.49
    POSITIVE LOGITS
     مرئيه
    0.91
     EconPapers
    0.67
     للمعارف
    0.65
    MessageOf
    0.63
    argout
    0.62
     ISNI
    0.62
     Roskov
    0.60
    FOREWORD
    0.57
    useNewUrlParser
    0.55
    ثيق
    0.55
    Activations Density 0.160%

    No Known Activations