© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 107502
    Prev
    Next
    INDEX
    Explanations

    elements and properties related to component structure in programming languages, particularly those used in front-end frameworks

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

    user input after start of turn

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
    onomía
    -0.52
    出版年
    -0.52
     gebru
    -0.41
    ⎩
    -0.40
     CURIAM
    -0.39
     Betracht
    -0.38
     gravedad
    -0.37
    pustakaan
    -0.37
    bindingNavigator
    -0.37
     internetowa
    -0.36
    POSITIVE LOGITS
    setArguments
    0.56
    EndContext
    0.52
    HomeAsUpEnabled
    0.51
     EconPapers
    0.46
    NavController
    0.45
     RouterModule
    0.44
     GenerationType
    0.42
    CloseOperation
    0.40
     NSCoder
    0.40
    onAttach
    0.39
    Activations Density 0.001%

    No Known Activations