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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 18-GEMMASCOPE-RES-16K
    6. 10594
    Prev
    Next
    INDEX
    Explanations

    elements related to the structure and implementation of a programming class in user interface design

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hyrchwyd
    -0.54
    ună
    -0.48
    getDouble
    -0.48
    ssch
    -0.44
    lazione
    -0.43
    чной
    -0.42
    منم
    -0.42
    ючи
    -0.42
     ruch
    -0.41
     vícti
    -0.41
    POSITIVE LOGITS
    ScopeManager
    0.80
    AnchorStyles
    0.77
    脚注の使い方
    0.75
    PYX
    0.75
     localObject
    0.74
    تقاوى
    0.73
    ArrowToggle
    0.73
    RegistryLite
    0.73
    yship
    0.65
    ValueStyle
    0.64
    Activations Density 0.022%

    No Known Activations