Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 10388
    Prev
    Next
    INDEX
    Explanations

    specific punctuation and formatting variations within the text

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

    numbers or codes

    np_acts-logits-general · gemini-2.0-flash

    questions and names

    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
    *}
    
    -0.60
    '))
    
    -0.60
     ')'
    -0.59
     للاسماء
    -0.57
    "))
    
    -0.57
    ":
    
    -0.55
    ]`
    -0.54
    ])
    
    -0.54
     care
    -0.54
    ='';
    
    -0.54
    POSITIVE LOGITS
    UserScript
    0.76
     doInBackground
    0.74
     resourceCulture
    0.73
     kasarigan
    0.70
     disponibilités
    0.63
    úgó
    0.62
    AntiForgeryToken
    0.62
    GraphicsUnit
    0.62
     GetEnumerator
    0.61
    存于互联网档案馆
    0.61
    Activations Density 0.514%

    No Known Activations