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. 13-GEMMASCOPE-RES-16K
    6. 14108
    Prev
    Next
    INDEX
    Explanations

    references to particles and their properties in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    webElement
    -0.84
    expandindo
    -0.83
    DebuggerNonUser
    -0.80
     surla
    -0.79
    Datuak
    -0.77
    FunctionFlags
    -0.77
    EndInit
    -0.76
    mybatisplus
    -0.75
     protoimpl
    -0.74
     BorderRadius
    -0.74
    POSITIVE LOGITS
    seamnă
    0.75
    راتيج
    0.66
     termica
    0.65
     pamamagitan
    0.65
     maș
    0.62
     vastaan
    0.62
     cauza
    0.62
     itſelf
    0.61
     Klon
    0.60
     preghi
    0.60
    Activations Density 0.498%

    No Known Activations