© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 3069
    Prev
    Next
    INDEX
    Explanations

    variable declarations and manipulations in programming contexts

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

    File paths or variables

    np_acts-logits-general · gemini-2.0-flash

    variable initializations in code

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    enumi
    -0.73
     للمعارف
    -0.66
     uncin
    -0.60
    NameInMap
    -0.57
    formation
    -0.55
    Formation
    -0.53
     AssemblyCulture
    -0.52
    Stor
    -0.50
     jspb
    -0.50
     Stor
    -0.49
    POSITIVE LOGITS
    žiaga
    0.49
     herido
    0.49
     sufrido
    0.49
     requerido
    0.48
     geométrico
    0.47
     detenido
    0.47
     zoude
    0.46
     fijo
    0.46
     afges
    0.46
     Moscú
    0.46
    Activations Density 0.371%

    No Known Activations