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

    Neuronpedia

    APICircuit 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. 38782
    Prev
    Next
    INDEX
    Explanations

    details related to design elements and materials used in vehicles or uniforms

    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
    MethodManager
    -0.37
    SourceChecksum
    -0.36
    '],'
    -0.36
    ]<<"
    -0.35
    *************
    -0.34
    quilo
    -0.33
    horizontalLayout
    -0.32
    ']='
    -0.32
     Kall
    -0.32
    ***********/
    -0.31
    POSITIVE LOGITS
     BorderSide
    0.77
     AttributeSet
    0.68
     فريبيس
    0.61
    DockStyle
    0.60
     lenker
    0.57
     AssemblyTitle
    0.54
     inlaid
    0.53
     linkovi
    0.52
     accents
    0.52
     &___
    0.51
    Activations Density 0.012%

    No Known Activations