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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 5664
    Prev
    Next
    INDEX
    Explanations

    phrases related to significant encounters and their implications

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

    foreign words and characters

    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
    rungsseite
    -0.84
     للمعارف
    -0.75
    Autoritní
    -0.71
    ImageContext
    -0.69
    GOTREF
    -0.68
    الدراسه
    -0.66
     CreateTagHelper
    -0.64
     defaultstate
    -0.63
    Carriera
    -0.63
    AutoField
    -0.61
    POSITIVE LOGITS
    Kjelder
    0.39
     forced
    0.29
    ეთ
    0.27
    pas
    0.26
     inget
    0.26
    强
    0.25
     moldura
    0.24
     def
    0.24
    teness
    0.24
    kör
    0.24
    Activations Density 0.165%

    No Known Activations