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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 3954
    Prev
    Next
    INDEX
    Explanations

    terms related to administrative or organizational concepts

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

    words ending in -ial or -orial

    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
     deſt
    -0.54
    Disconnect
    -0.53
     estabiliz
    -0.51
     climático
    -0.51
     quæ
    -0.50
     Physik
    -0.49
     anhänger
    -0.49
     houſe
    -0.49
     Défense
    -0.48
    BirthDate
    -0.48
    POSITIVE LOGITS
    orial
    1.66
    atorial
    1.48
    arial
    1.23
    ORIAL
    1.12
     pictorial
    1.03
    itorial
    0.93
     Ministerial
    0.91
     ministerial
    0.90
     Managerial
    0.81
    erial
    0.79
    Activations Density 0.012%

    No Known Activations