© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 2820
    Prev
    Next
    INDEX
    Explanations

    references to viral structures and their variants

    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
    RegressionTest
    -0.65
    tagHelperRunner
    -0.64
     ब्रेकडाउन
    -0.57
    EndGlobalSection
    -0.53
    outState
    -0.52
     للاسماء
    -0.51
     Infórmanos
    -0.51
    AndEndTag
    -0.50
    InSection
    -0.49
    ंदीखरीदारी
    -0.48
    POSITIVE LOGITS
    ModelAdmin
    0.45
     specifically
    0.35
    łaszcza
    0.34
    PreAuthorize
    0.34
    specific
    0.33
    testens
    0.33
     consumers
    0.33
     rass
    0.33
     espec
    0.32
     manifeste
    0.32
    Activations Density 1.033%

    No Known Activations