© 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. 9-GEMMASCOPE-RES-131K
    11. 23539
    Prev
    Next
    INDEX
    Explanations

    formatting or structural elements in a document, such as LaTeX commands and mathematical expressions

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

    LaTeX math and code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nemlig
    -0.56
    vajal
    -0.47
     bénévol
    -0.46
    เอง
    -0.45
     aberta
    -0.44
     bowiem
    -0.43
     aberto
    -0.42
     nämlich
    -0.42
     voluntarios
    -0.42
     afspraak
    -0.42
    POSITIVE LOGITS
     nahilalakip
    0.74
    QMetaType
    0.50
    IsContent
    0.49
     kaarangay
    0.49
     snippetHide
    0.48
    AccessorTable
    0.47
     يتيمه
    0.46
     оригіналу
    0.46
    ArgsConstructor
    0.45
    Personendaten
    0.45
    Activations Density 0.003%

    No Known Activations