© 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 - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 115005
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate marketing or promotional language

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

    presenting as

    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
     resourceCulture
    -0.45
    gbc
    -0.45
     Reverso
    -0.44
    guous
    -0.42
     gbc
    -0.40
     tula
    -0.39
    Données
    -0.38
    eated
    -0.38
     criteria
    -0.38
    adə
    -0.38
    POSITIVE LOGITS
     marketed
    0.72
     billed
    0.67
     touted
    0.59
     advertised
    0.57
     nabíz
    0.53
    billed
    0.48
    ientôt
    0.46
     MainAxisSize
    0.46
     Vordergrund
    0.44
    adverti
    0.43
    Activations Density 0.020%

    No Known Activations