© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 35643
    Prev
    Next
    INDEX
    Explanations

    concepts related to graph theory and the rules of separation between nodes in directed acyclic graphs (DAGs)

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

    d-separated from rules

    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
    뀜
    -0.37
     AssemblyCompany
    -0.34
     animate
    -0.31
     pubblici
    -0.31
    enumii
    -0.30
     mese
    -0.30
     presa
    -0.30
     respir
    -0.30
    Сере
    -0.30
    },[])
    -0.29
    POSITIVE LOGITS
     gossi
    0.70
    DeleteBehavior
    0.65
    gossip
    0.65
     gossip
    0.64
     iprot
    0.61
    verwijspagina
    0.61
    TypedDataSet
    0.59
    rungsseite
    0.58
     betweenstory
    0.57
    aarrggbb
    0.56
    Activations Density 0.290%

    No Known Activations