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. 10-GEMMASCOPE-RES-16K
    6. 13013
    Prev
    Next
    INDEX
    Explanations

    references to characteristics of thickness in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    — 
    -0.69
    er
    -0.64
    stdlib
    -0.61
    UT
    -0.60
    ();
    
    
    -0.60
     Andy
    -0.59
     Wim
    -0.59
    – 
    -0.57
    >
    
    
    -0.57
     địa
    -0.57
    POSITIVE LOGITS
     thickening
    0.97
     trajets
    0.91
     supérieurs
    0.90
    Jacobs
    0.88
     Thick
    0.86
     thicken
    0.85
    ftagPool
    0.85
     Thickness
    0.85
     onCancelled
    0.85
     Bekasi
    0.84
    Activations Density 0.217%

    No Known Activations