© 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. 9-GEMMASCOPE-RES-131K
    6. 12289
    Prev
    Next
    INDEX
    Explanations

    references to sports teams and legal terminology

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

    Rams, Ram, Aries, ram

    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
     Boucher
    -0.52
    Karin
    -0.50
    isEdit
    -0.50
    julie
    -0.47
     Vitale
    -0.47
    Salsa
    -0.47
     Eriksson
    -0.46
     simul
    -0.46
    imwrite
    -0.46
    存于互联网档案馆
    -0.46
    POSITIVE LOGITS
     Rams
    2.39
    Rams
    2.06
     rams
    1.18
     Ramsay
    0.99
    rams
    0.92
     Ram
    0.73
     RAM
    0.72
     auroit
    0.69
     Romains
    0.67
    RAM
    0.65
    Activations Density 0.005%

    No Known Activations