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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 9-GEMMASCOPE-RES-16K
    6. 7890
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to SEO (Search Engine Optimization) and search queries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    liang
    -0.71
     Crot
    -0.71
     mener
    -0.67
     Liang
    -0.67
     Asbury
    -0.66
    Bres
    -0.62
     للمعارف
    -0.61
     Rath
    -0.59
     Kashi
    -0.59
    graphi
    -0.59
    POSITIVE LOGITS
    Se
    1.56
     Se
    1.54
     SE
    1.41
     Selig
    1.31
     Seitz
    1.26
     Seidel
    1.26
    SE
    1.26
     Searle
    1.22
     Seva
    1.16
     se
    1.16
    Activations Density 0.117%

    No Known Activations