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
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 10286
    Prev
    Next
    INDEX
    Explanations

    references to health-related conditions and products, particularly those involving hemp and video content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.53
    gelegt
    -0.53
    /**
    -0.50
     AssemblyCompany
    -0.47
    timewa
    -0.47
     autorytatywna
    -0.46
     Савез
    -0.44
    gegangen
    -0.44
     pageContext
    -0.44
     gynhyrchwyd
    -0.44
    POSITIVE LOGITS
     gummies
    0.54
     oil
    0.48
     sleep
    0.44
    saraba
    0.42
     Sleep
    0.42
    Tikang
    0.39
     isolate
    0.38
     capsules
    0.38
     Oil
    0.37
     sommeil
    0.36
    Activations Density 0.234%

    No Known Activations