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
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 122984
    Prev
    Next
    INDEX
    Explanations

    keywords related to events and activities in technology and media contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
     EconPapers
    -0.46
    retudo
    -0.46
    autaire
    -0.45
    stretchr
    -0.45
     محفوظة
    -0.45
     maleta
    -0.45
    mbalikan
    -0.45
    undidad
    -0.44
     costumbre
    -0.44
    udahkan
    -0.44
    POSITIVE LOGITS
    IUrlHelper
    0.57
     Roskov
    0.55
    RectangleBorder
    0.49
    CodedInputStream
    0.45
     Numerade
    0.41
    )_/¯
    0.40
     <>",
    0.39
     Taktlose
    0.38
    (!__
    0.37
    VolleyError
    0.37
    Activations Density 0.070%

    No Known Activations