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. 5-GEMMASCOPE-RES-16K
    6. 3030
    Prev
    Next
    INDEX
    Explanations

    sections of text that indicate null or negligible content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ...";
    -0.91
    ...");
    
    -0.89
    .";
    
    -0.82
     faſt
    -0.74
     contextLoads
    -0.72
    ">*</
    -0.72
     raiſ
    -0.71
     iſt
    -0.71
     tartalomajánló
    -0.71
    berdayakan
    -0.69
    POSITIVE LOGITS
    <bos>
    0.79
     ت
    0.65
     ش
    0.64
    脚注の使い方
    0.62
     
    0.62
    évaluateur
    0.62
    酒
    0.61
      
    0.61
     ال
    0.60
     स
    0.60
    Activations Density 0.058%

    No Known Activations