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. 18-GEMMASCOPE-RES-16K
    6. 8578
    Prev
    Next
    INDEX
    Explanations

    HTML/XML-like tags and structure within the text

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

    Code delimiters and special characters

    np_acts-logits-general · gemini-2.0-flash

    code delimiters `><`, `>`, `%{`, `=`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BibitemShut
    -1.01
     itſelf
    -0.98
     Theſe
    -0.98
    !")
    
    -0.93
    )++;
    -0.93
     myſelf
    -0.92
    .³
    -0.91
     ―――――
    -0.89
     ''
    
    -0.89
     مشين
    -0.88
    POSITIVE LOGITS
      
    0.55
    ikian
    0.46
    ↵
    0.45
        
    0.44
     
    0.41
    udades
    0.41
    S
    0.41
     unsafe
    0.41
    <eos>
    0.41
     d
    0.40
    Activations Density 4.562%

    No Known Activations