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. 21-GEMMASCOPE-RES-16K
    6. 5664
    Prev
    Next
    INDEX
    Explanations

    business partnerships and collaborations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     impuestos
    -0.46
     Accesorios
    -0.45
     policiales
    -0.43
    Bibliograf
    -0.42
    nhung
    -0.42
     hjemmeside
    -0.41
     beginnetje
    -0.41
     antidesliz
    -0.40
     Herramientas
    -0.39
     láser
    -0.39
    POSITIVE LOGITS
     partnering
    0.89
     partnership
    0.89
     collaboration
    0.88
     partner
    0.84
     partners
    0.83
     partnerships
    0.81
    collaboration
    0.80
    partnership
    0.80
     partnered
    0.77
     collaborating
    0.77
    Activations Density 0.233%

    No Known Activations