© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 3656
    Prev
    Next
    INDEX
    Explanations

    sentiments related to customer service and business communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    出版年
    -0.60
    verwijspagina
    -0.53
     punished
    -0.53
     Vikipedi
    -0.51
    规律
    -0.50
     punish
    -0.49
     lato
    -0.47
    ]++;
    -0.47
     boycott
    -0.47
     gyhoeddwyd
    -0.46
    POSITIVE LOGITS
     quote
    0.90
     estimate
    0.88
     quotes
    0.87
     discuss
    0.86
     consultation
    0.85
     quotation
    0.85
     Estimate
    0.83
     presupuesto
    0.81
     quotations
    0.78
     discussing
    0.77
    Activations Density 0.173%

    No Known Activations