Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 30017
    Prev
    Next
    INDEX
    Explanations

    attributes and qualities related to imperfections and characteristics that contribute to the uniqueness of items or experiences

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

    making things better

    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
     للاسماء
    -0.57
     FetchType
    -0.55
     Infór
    -0.54
     Efq
    -0.54
     resourceCulture
    -0.54
     Normdatei
    -0.52
    ItemBackground
    -0.52
     queſto
    -0.51
    ExecuteReader
    -0.49
    Життєпис
    -0.49
    POSITIVE LOGITS
    NullCheck
    0.31
    ledning
    0.31
     çanta
    0.30
     jenner
    0.30
     bordada
    0.29
    처
    0.29
    fontawesome
    0.29
    ༘
    0.28
    ViewChild
    0.28
    Fon
    0.28
    Activations Density 0.029%

    No Known Activations