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 - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 1067
    Prev
    Next
    INDEX
    Explanations

    rewrite rules and code configuration related to web servers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    code-related functions and commands, particularly those involving CSS minification and processing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    URL redirection and code constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    URLException
    -0.62
    KEYCODE
    -0.61
     الدولى
    -0.54
    WebElementEntity
    -0.54
    BeforeMethod
    -0.51
    oughs
    -0.50
    principalColumn
    -0.49
    propTypes
    -0.49
     arşivlendi
    -0.49
    ❉
    -0.48
    POSITIVE LOGITS
     يتيمه
    0.70
    loader
    0.66
    SequentialGroup
    0.64
     loader
    0.56
    loaders
    0.55
    InjectMocks
    0.54
     loaders
    0.54
     useStyles
    0.52
    Rifer
    0.51
     contextLoads
    0.51
    Activations Density 0.013%

    No Known Activations