© 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. 22008
    Prev
    Next
    INDEX
    Explanations

    conjunctions and linking words that coordinate ideas or elements within sentences

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

    maintain and improve

    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
    tonode
    -0.55
     Autorizaciones
    -0.54
    imageshack
    -0.49
     createState
    -0.48
    prehension
    -0.47
    évaluateur
    -0.46
    StoryboardSegue
    -0.46
    +#+#
    -0.45
    __;
    -0.45
    databinding
    -0.44
    POSITIVE LOGITS
     eventualmente
    0.54
     eventually
    0.49
    eventually
    0.48
    Eventually
    0.47
     gradually
    0.47
     Gradually
    0.46
     Eventually
    0.45
    Occasionally
    0.45
    たまに
    0.45
     occasionally
    0.43
    Activations Density 0.061%

    No Known Activations