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. 10-GEMMASCOPE-RES-16K
    6. 10887
    Prev
    Next
    INDEX
    Explanations

    programming-related class and method declarations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.67
    agaimana
    -0.62
    =$?
    -0.61
     '\\;'
    -0.60
     Efq
    -0.60
     loob
    -0.58
    berdayakan
    -0.58
    mappedBy
    -0.56
    <bos>
    -0.56
    principalColumn
    -0.56
    POSITIVE LOGITS
    </em>
    0.73
    CharStream
    0.63
    setVerticalGroup
    0.62
    </code>
    0.59
        
    0.59
     [
    0.56
       
    0.56
    </u>
    0.55
    ULLY
    0.54
      
    0.53
    Activations Density 0.659%

    No Known Activations