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. 5-GEMMASCOPE-RES-16K
    6. 3406
    Prev
    Next
    INDEX
    Explanations

    instances of mathematical alignment environments in LaTeX code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +"/"+
    -0.50
     customers
    -0.49
     clients
    -0.49
     Doreen
    -0.49
     htons
    -0.48
     Cuth
    -0.47
     bit
    -0.47
    oporosis
    -0.47
    hånd
    -0.46
     consumers
    -0.46
    POSITIVE LOGITS
    aligned
    2.68
     aligned
    1.56
    Aligned
    1.31
     Alignment
    1.29
     alignment
    1.26
    align
    1.20
    alignment
    1.19
     Align
    1.18
     ALIGN
    1.17
     align
    1.14
    Activations Density 0.042%

    No Known Activations