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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 105160
    Prev
    Next
    INDEX
    Explanations

    specific programming syntax and commands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    InstrumentedTest
    -0.59
    最快更新
    -0.57
     AssemblyCompany
    -0.54
    Билгалдахарш
    -0.52
    LookAnd
    -0.52
     Paglinawan
    -0.50
     sondern
    -0.49
     nakalista
    -0.48
     wikipagina
    -0.46
    LayoutPanel
    -0.46
    POSITIVE LOGITS
    makeText
    0.50
    nonatomic
    0.47
    KommentareTeilen
    0.44
    InputTagHelper
    0.43
    SequentialGroup
    0.42
     '\\;'
    0.41
    CppCodeGen
    0.40
    hasMoreElements
    0.38
     previo
    0.36
    ļi
    0.36
    Activations Density 0.164%

    No Known Activations