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. 4-GEMMASCOPE-RES-16K
    6. 10993
    Prev
    Next
    INDEX
    Explanations

    instances of alignment and its variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -1.00
    ंदीखरीदारी
    -0.93
    
    -0.90
    ⓧ
    -0.87
     NSCoder
    -0.86
     CreateTagHelper
    -0.85
    انيف
    -0.84
     المعيارى
    -0.75
    Jeografia
    -0.75
    principalColumn
    -0.73
    POSITIVE LOGITS
     alignment
    1.55
     Alignment
    1.49
     aligns
    1.43
     aligned
    1.43
     aligning
    1.39
     alignments
    1.33
     align
    1.32
     ALIGN
    1.30
    alignment
    1.28
    aligned
    1.25
    Activations Density 0.124%

    No Known Activations