© 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. 107254
    Prev
    Next
    INDEX
    Explanations

    terms related to a patient-centered or user-centric approach in research and healthcare

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

    centered or focused on specific entities

    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
    RegisterType
    -0.46
    щадь
    -0.37
     unwit
    -0.35
     downloading
    -0.35
     trivia
    -0.35
     subscribers
    -0.35
     Stimmung
    -0.34
     infecting
    -0.34
     subscribing
    -0.34
     unin
    -0.33
    POSITIVE LOGITS
    centered
    1.43
    centred
    1.41
    Centered
    1.28
     centred
    1.05
     centered
    1.00
    centric
    0.96
    focused
    0.82
     Focused
    0.80
     centric
    0.79
    Focused
    0.79
    Activations Density 0.007%

    No Known Activations