© 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. 31-GEMMASCOPE-RES-131K
    11. 88013
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to urgent needs and support in various contexts

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

    needed or necessary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StoryboardSegue
    -0.64
    httphttps
    -0.57
    etCode
    -0.56
    featureID
    -0.55
    InjectAttribute
    -0.54
    transQ
    -0.53
    TestingModule
    -0.53
    الحياه
    -0.53
    WebVitals
    -0.53
     TAMBÉM
    -0.52
    POSITIVE LOGITS
     needed
    1.94
    needed
    1.72
     necessary
    1.61
     Needed
    1.59
    Needed
    1.50
     NEEDED
    1.43
    necessary
    1.35
     necesaria
    1.30
     Necessary
    1.28
     necesario
    1.23
    Activations Density 0.089%

    No Known Activations