© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 36-GEMMASCOPE-RES-16K
    6. 15921
    Prev
    Next
    INDEX
    Explanations

    terms related to organizations, associations, and their activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     comigo
    -0.32
     Picchu
    -0.29
     stanow
    -0.29
     Flucht
    -0.28
     leher
    -0.27
     croissance
    -0.26
     NSCoder
    -0.26
     وصلة
    -0.26
     sentarse
    -0.26
     aload
    -0.25
    POSITIVE LOGITS
     association
    2.09
     organization
    1.93
     Association
    1.93
     associations
    1.91
     organisation
    1.87
    association
    1.86
    Association
    1.84
     ASSOCIATION
    1.76
     Associations
    1.72
     organizations
    1.71
    Activations Density 0.982%

    No Known Activations