© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 84023
    Prev
    Next
    INDEX
    Explanations

    symbols and characters used in programming or markup code

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

    templating delimiters `{{` and `}}`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     paroles
    -0.40
    PORARY
    -0.40
     temporarily
    -0.39
     keduanya
    -0.38
    暂
    -0.35
     queſta
    -0.35
     gewöhnlich
    -0.35
     cœurs
    -0.35
    addPreferredGap
    -0.34
     Walkover
    -0.34
    POSITIVE LOGITS
    RegistryLite
    0.57
    WireFormatLite
    0.53
     otomatig
    0.51
    存于互联网档案馆
    0.48
    ########.
    0.47
    FormTagHelper
    0.45
     title
    0.45
    principalTable
    0.45
     kaarangay
    0.44
     Title
    0.44
    Activations Density 0.003%

    No Known Activations