© 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. 9011
    Prev
    Next
    INDEX
    Explanations

    references to past events and temporal expressions

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

    know beforehand, apart, least

    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
    featureID
    -0.45
     Inſ
    -0.44
    Diwedd
    -0.42
     juſ
    -0.41
    PreferredItem
    -0.41
     calendriers
    -0.40
     ſta
    -0.40
    Collegamenti
    -0.40
    piew
    -0.39
     purpoſe
    -0.39
    POSITIVE LOGITS
     know
    1.11
    Know
    1.08
    know
    1.01
     Know
    1.00
     KNOW
    0.95
     knows
    0.94
     knew
    0.90
    knows
    0.87
     knowledge
    0.86
     Knew
    0.86
    Activations Density 0.203%

    No Known Activations