© 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. 6591
    Prev
    Next
    INDEX
    Explanations

    references to processes and processing within code or technical documentation

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

    process and associated terms

    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
    Toponymie
    -0.39
     estimés
    -0.38
     näky
    -0.35
    delà
    -0.35
     facteur
    -0.34
    ACIONAL
    -0.34
    UnusedPrivate
    -0.34
     créateur
    -0.34
    SelectedItem
    -0.33
     Sábado
    -0.33
    POSITIVE LOGITS
    Process
    2.75
     Process
    2.69
     PROCESS
    2.27
    PROCESS
    2.17
    process
    2.17
     process
    2.03
     Processes
    1.85
    Proces
    1.75
     Proces
    1.73
     Prozess
    1.72
    Activations Density 0.012%

    No Known Activations