© 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. 50282
    Prev
    Next
    INDEX
    Explanations

    specific programming language data types, indicating a focus on coding or technical content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     betweenstory
    -0.83
     يتيمه
    -0.70
     queſta
    -0.68
    Personendaten
    -0.59
    polation
    -0.59
     JpaRepository
    -0.56
     متعلقه
    -0.55
    səhifə
    -0.52
     getSystem
    -0.52
    atshirt
    -0.51
    POSITIVE LOGITS
    Text
    0.58
    setupUi
    0.49
     AssemblyCompany
    0.45
    Tasks
    0.45
    UnitTesting
    0.43
     ExecuteAsync
    0.43
     "..\..\..\
    0.42
     []:
    0.41
    MigrationBuilder
    0.40
    '}';
    0.40
    Activations Density 0.000%

    No Known Activations