© 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 EvalsExportsinterp-engineNEWAPI 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. 60391
    Prev
    Next
    INDEX
    Explanations

    function names related to creating and managing objects

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

    create new or get first

    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
     fileSize
    -0.57
    ivores
    -0.56
     accountId
    -0.54
     newUser
    -0.53
    プーン
    -0.52
     roomId
    -0.52
     imagePath
    -0.52
     imageUrl
    -0.52
    FACE
    -0.52
    +#+
    -0.51
    POSITIVE LOGITS
    addNew
    1.48
     addNew
    1.39
    AddNew
    1.26
    createNew
    0.98
     createNew
    0.90
    getNext
    0.73
    GetNext
    0.66
    getNew
    0.65
    setNew
    0.63
     getNew
    0.60
    Activations Density 0.007%

    No Known Activations