© 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. 18-GEMMASCOPE-RES-16K
    11. 1722
    Prev
    Next
    INDEX
    Explanations

    sections of the text with no significant data or content

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

    Code, questions, and abbreviations

    np_acts-logits-general · gemini-2.0-flash

    bash script starters

    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
     ujednoznacz
    -0.87
     AssemblyCulture
    -0.80
     disambiguazione
    -0.75
    WithIOException
    -0.67
    (__('
    -0.65
    WebVitals
    -0.64
     виправивши
    -0.64
    spesies
    -0.62
    脚注の使い方
    -0.62
    Rhestr
    -0.62
    POSITIVE LOGITS
    <eos>
    1.21
    </tr>
    0.94
    [toxicity=0]
    0.92
        
    0.90
    ↵↵
    0.82
    ↵↵↵↵↵
    0.80
      
    0.76
            
    0.76
    ↵↵↵↵
    0.74
    ↵↵↵↵↵↵
    0.74
    Activations Density 0.093%

    No Known Activations