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. 36574
    Prev
    Next
    INDEX
    Explanations

    phrases related to free items and applications

    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
    zzleHttp
    -0.63
     EconPapers
    -0.50
    Kariera
    -0.48
    WriteTagHelper
    -0.47
    RRect
    -0.46
    شهاد
    -0.45
    SequentialGroup
    -0.44
    CharStream
    -0.43
    umel
    -0.42
    σμο
    -0.42
    POSITIVE LOGITS
     gratis
    0.56
     HttpNotFound
    0.53
     رایگان
    0.50
    免費
    0.49
     gratuitement
    0.49
     бесплатно
    0.48
    Gratis
    0.48
     free
    0.48
     Gratis
    0.47
    gratis
    0.45
    Activations Density 0.078%

    No Known Activations