© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 5622
    Prev
    Next
    INDEX
    Explanations

    punctuation or structural elements in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ſcher
    -0.77
     feroit
    -0.76
    iſchen
    -0.75
     increí
    -0.74
    iſen
    -0.72
    ſſung
    -0.70
    ésultats
    -0.69
    ðsíða
    -0.69
    majánló
    -0.69
    niſſe
    -0.68
    POSITIVE LOGITS
      
    0.56
     
    0.53
    <b>
    0.50
    ↵
    0.47
            
    0.46
    *
    0.46
    <strong>
    0.46
    <th>
    0.44
                  
    0.43
        
    0.43
    Activations Density 0.051%

    No Known Activations