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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 7888
    Prev
    Next
    INDEX
    Explanations

    terms related to equality and comparison in programming or mathematical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    createCanvas
    -0.49
     FetchType
    -0.49
    PreExecute
    -0.49
     jScrollPane
    -0.46
     المعيارى
    -0.45
     Signalez
    -0.44
     MenuView
    -0.44
    Datuak
    -0.43
    autoreleasepool
    -0.42
    EndGlobalSection
    -0.42
    POSITIVE LOGITS
     differences
    0.61
     similarity
    0.59
     similarities
    0.57
     Similarity
    0.53
     identical
    0.50
     SIMILAR
    0.50
     Unterschiede
    0.48
    differences
    0.48
     Differences
    0.47
     mergeFrom
    0.45
    Activations Density 1.230%

    No Known Activations