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. 8-GEMMASCOPE-RES-16K
    6. 8097
    Prev
    Next
    INDEX
    Explanations

    references to data structure operations, particularly those involving arrays and collections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icose
    -0.54
     &___
    -0.52
    samt
    -0.49
    bellar
    -0.48
     inter
    -0.45
    вге
    -0.45
    selaer
    -0.44
    Inter
    -0.44
    Salut
    -0.43
    engeti
    -0.42
    POSITIVE LOGITS
    tagHelperRunner
    1.32
    DockStyle
    1.18
    mergeFrom
    0.96
    Према
    0.95
    FormTagHelper
    0.89
    ArgumentParser
    0.89
     myſelf
    0.88
    TagHelper
    0.87
     initComponents
    0.83
    gameserver
    0.83
    Activations Density 0.011%

    No Known Activations