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. 10-GEMMASCOPE-RES-16K
    6. 3057
    Prev
    Next
    INDEX
    Explanations

    syntax and structure related to JavaScript unit testing frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __':
    
    -1.00
    RegistryLite
    -1.00
     resourceCulture
    -0.91
    Rhestr
    -0.87
    MigrationBuilder
    -0.86
    __":
    
    -0.81
    ArgsConstructor
    -0.79
    AndEndTag
    -0.78
     @"/
    -0.78
    #+#
    -0.78
    POSITIVE LOGITS
    describe
    1.20
    RSpec
    0.66
    Describe
    0.65
    beforeEach
    0.60
     Behav
    0.59
    bited
    0.58
     digitais
    0.56
    groupBox
    0.56
    Rit
    0.54
    ReactDOM
    0.51
    Activations Density 0.031%

    No Known Activations