© 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. 37895
    Prev
    Next
    INDEX
    Explanations

    phrase structures related to dependencies and relationships in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    rrggbb
    -0.53
    +:+
    -0.45
     Riproduzione
    -0.42
    fromnode
    -0.42
     TextInputType
    -0.40
     autorytatywna
    -0.40
    visiae
    -0.40
    ">//
    -0.38
    TRIBUN
    -0.36
     inoltre
    -0.36
    POSITIVE LOGITS
    Lähteet
    0.54
    haikusbot
    0.52
    IUrlHelper
    0.47
     MEM
    0.42
    ]--;
    0.41
     Pote
    0.41
    olverine
    0.41
    ',[
    0.39
     ALLOW
    0.39
    telephone
    0.39
    Activations Density 0.103%

    No Known Activations