© 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. 20-GEMMASCOPE-RES-131K
    6. 119292
    Prev
    Next
    INDEX
    Explanations

    phrases related to interpersonal dynamics and conflicts

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

    defendants press

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OGND
    -0.49
     informée
    -0.44
    ogli
    -0.40
    ylem
    -0.40
    photon
    -0.40
    úgó
    -0.40
    jos
    -0.39
    uba
    -0.38
    ombe
    -0.38
    Mule
    -0.38
    POSITIVE LOGITS
    rawDesc
    0.61
     propOrder
    0.53
     insuffisamment
    0.50
    LookAnd
    0.47
     CreateTagHelper
    0.46
    OCCURRED
    0.45
    MessageOf
    0.44
    Geplaatst
    0.43
    fjspx
    0.43
    Diweddarwch
    0.42
    Activations Density 0.175%

    No Known Activations