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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 37-GEMMASCOPE-RES-16K
    6. 5719
    Prev
    Next
    INDEX
    Explanations

    references to online advertising mechanisms and user engagement practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nahilalakip
    -0.42
     hikariConfig
    -0.36
     Stufen
    -0.36
     OFDb
    -0.36
    мят
    -0.36
    glVertex
    -0.35
    盯着
    -0.35
    shed
    -0.35
     שוליים
    -0.35
     <<<<<<<<<<<<<<
    -0.34
    POSITIVE LOGITS
     search
    3.22
     Search
    2.78
    search
    2.77
    Search
    2.58
     SEARCH
    2.55
     searches
    2.45
     searched
    2.33
    SEARCH
    2.33
    搜索
    2.23
     Searches
    2.06
    Activations Density 0.708%

    No Known Activations