© 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. 128145
    Prev
    Next
    INDEX
    Explanations

    references to property descriptors in programming contexts

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

    descriptor and spectator

    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
     ſame
    -0.53
     betweenstory
    -0.52
     utafitiHapana
    -0.51
    runApp
    -0.51
     ſtre
    -0.50
    Política
    -0.50
    IVEREF
    -0.50
    fromnode
    -0.50
    multer
    -0.49
     CanadaChoose
    -0.49
    POSITIVE LOGITS
    Descriptor
    3.44
     Descriptor
    2.09
    Descriptors
    1.66
    DESCRIPTOR
    1.51
    descriptor
    1.47
     descriptor
    1.35
    getDescriptor
    1.29
     Descriptors
    1.23
    descriptors
    1.20
    FieldDescriptor
    1.09
    Activations Density 0.001%

    No Known Activations