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-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 13992
    Prev
    Next
    INDEX
    Explanations

    questions and responses in a conversational or legal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Questions and answers

    np_acts-logits-general · gemini-2.0-flash

    followed by colon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    '):
    
    -0.99
    "]);
    
    -0.97
    ")]
    
    -0.96
    '))
    
    -0.96
    %")
    -0.94
    "))
    
    -0.94
    "):
    
    -0.94
    "]))
    -0.93
    '])
    
    -0.92
    })$}
    -0.92
    POSITIVE LOGITS
     مواليد
    0.61
     muualla
    0.58
     câte
    0.52
     dép
    0.51
    :✨
    0.50
     esternos
    0.49
    yorsunuz
    0.49
    ,:
    0.49
     gerekiyor
    0.49
     recevez
    0.48
    Activations Density 0.159%

    No Known Activations