© 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. 52309
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the presence of specific content

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

    word contained

    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
     armée
    -0.47
     congé
    -0.46
    qrst
    -0.45
    archiviato
    -0.45
    helps
    -0.44
     Infór
    -0.44
     Italijani
    -0.44
     élimin
    -0.44
    Tipps
    -0.43
     Armas
    -0.43
    POSITIVE LOGITS
     contained
    1.97
    contained
    1.75
    Contained
    1.45
     conten
    0.97
     CONTAIN
    0.94
     containment
    0.93
     contenus
    0.83
     Containment
    0.82
     contenuto
    0.81
     enclosed
    0.75
    Activations Density 0.011%

    No Known Activations