© 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. 66165
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to similarity and resemblance

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

    likeness and similarity

    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
    WaitGroup
    -0.60
     للاسماء
    -0.56
    iastes
    -0.53
    İstinadlar
    -0.51
     Autorisations
    -0.50
     Pryor
    -0.49
    ustris
    -0.49
    argout
    -0.49
     المعيارى
    -0.48
    cfm
    -0.48
    POSITIVE LOGITS
     resemble
    0.86
     resembling
    0.72
     resembles
    0.70
     resembled
    0.68
     resemblance
    0.64
     ressemb
    0.55
     ressemble
    0.54
     resemb
    0.53
     giống
    0.43
    模样
    0.42
    Activations Density 0.025%

    No Known Activations